© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3145
    Prev
    Next
    INDEX
    Explanations

    words in a variety of contexts consisting of proper nouns, adjectives, parts of words, and code.

    oai_token-act-pair · gemini-2.0-flash

    language, text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     continúas
    -0.48
    MultipartFile
    -0.44
    TRIBUN
    -0.44
    eqn
    -0.44
     continuant
    -0.43
     createContext
    -0.43
    +#+
    -0.43
    tamol
    -0.42
    tfrac
    -0.42
     pinulongan
    -0.41
    POSITIVE LOGITS
    se
    0.90
    ses
    0.82
    sa
    0.81
    so
    0.81
    sp
    0.81
    sh
    0.80
    simp
    0.80
    ser
    0.79
    sy
    0.79
    san
    0.79
    Activations Density 5.078%

    No Known Activations