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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5268
    Prev
    Next
    INDEX
    Explanations

    articles followed by adjectives and nouns

    oai_token-act-pair · gemini-2.0-flash

    terms related to collections or groups

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

    Group of things

    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
    TabIndex
    -0.69
    يكب
    -0.67
    ArgsConstructor
    -0.66
    UserScript
    -0.63
     &___
    -0.59
    EndProject
    -0.59
     obcí
    -0.56
    enschappelijke
    -0.53
    CppMethod
    -0.53
    :][
    -0.53
    POSITIVE LOGITS
     collection
    1.50
     series
    1.40
     array
    1.32
    collection
    1.30
     list
    1.27
     assortment
    1.27
     set
    1.22
     conjunto
    1.16
    series
    1.13
     suite
    1.13
    Activations Density 2.736%

    No Known Activations