Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 948
    Prev
    Next
    INDEX
    Explanations

    legal citations

    oai_token-act-pair · gemini-2.0-flash

    WL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    RenderAtEndOf
    -0.53
     forceps
    -0.51
     myſelf
    -0.50
    YTA
    -0.49
     syphilis
    -0.48
     amnesia
    -0.47
    permitAll
    -0.47
     xenia
    -0.47
     Chaldean
    -0.47
     polycarbonate
    -0.47
    POSITIVE LOGITS
    abestanden
    0.85
    #
    0.72
    AddTagHelper
    0.71
    Билгалдахарш
    0.69
    artifactId
    0.66
    بوابة
    0.64
    Jeografia
    0.63
    resave
    0.60
    AxisAlignment
    0.60
     CreateTagHelper
    0.60
    Activations Density 3.620%

    No Known Activations