© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8663
    Prev
    Next
    INDEX
    Explanations

    a variety of positive words and phrases related to success, magnitude, and finance.

    oai_token-act-pair · gemini-2.0-flash

    describes surprise

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    WithMany
    -0.61
    ***************/
    -0.57
    HtmlAttribute
    -0.57
    IntoConstraints
    -0.57
    ModelAdmin
    -0.56
    fond
    -0.51
    GIVEREF
    -0.49
    těte
    -0.49
    )++;
    -0.48
    parsedMessage
    -0.47
    POSITIVE LOGITS
     aston
    0.87
     rivals
    0.84
     rival
    0.79
     surpassed
    0.74
     surpass
    0.73
     shocked
    0.71
     beggar
    0.69
     Rival
    0.69
     exceeded
    0.69
     baffle
    0.68
    Activations Density 2.951%

    No Known Activations