© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4546
    Prev
    Next
    INDEX
    Explanations

    references to comic books and superheroes, especially those from Marvel and DC.

    oai_token-act-pair · gemini-2.0-flash

    foreign 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ->__
    -0.52
     وا
    -0.44
    yntaxException
    -0.43
     form
    -0.43
     FORM
    -0.43
    componentWill
    -0.43
    ijo
    -0.42
     inter
    -0.42
     mental
    -0.41
     valueOf
    -0.41
    POSITIVE LOGITS
     ujednoznacz
    0.76
    出版年
    0.76
     Wikimedijinoj
    0.65
    GrantedAuthority
    0.63
    ruptedException
    0.62
    ToAction
    0.59
     مواليد
    0.59
    Begriffsklä
    0.59
    DockStyle
    0.59
     pleaſure
    0.59
    Activations Density 0.470%

    No Known Activations