© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3118
    Prev
    Next
    INDEX
    Explanations

    a varied collection of fairly common words, including verbs, nouns, and adjectives, along with some stop words

    oai_token-act-pair · gemini-2.0-flash

    references or citations in various languages

    np_token-act-pair-logits · gpt-4o-mini

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.79
    LookAnd
    -0.76
    InitVars
    -0.73
    oredCriteria
    -0.72
     nahilalakip
    -0.71
    )}</
    -0.68
    BeginInit
    -0.68
     <<<<<<<<<<<<<<
    -0.67
     referenties
    -0.67
     RIPRODUZIONE
    -0.67
    POSITIVE LOGITS
    Παραπομπές
    0.42
    staticmethod
    0.42
     rhestr
    0.42
     استنادى
    0.41
    Font
    0.41
     dejado
    0.41
     Co
    0.40
     molho
    0.39
     насељу
    0.39
    ⚽
    0.39
    Activations Density 1.703%

    No Known Activations