© 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. 1717
    Prev
    Next
    INDEX
    Explanations

    the word "none" or "no" followed by "of"

    oai_token-act-pair · gemini-2.0-flash

    none

    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
     Majefty
    -0.83
     Eſ
    -0.77
     ſeveral
    -0.76
     Reſ
    -0.75
    ſelf
    -0.74
     Efq
    -0.73
     Diſ
    -0.72
     Jefus
    -0.71
     Monfieur
    -0.69
     leaſt
    -0.68
    POSITIVE LOGITS
    Legături
    0.53
     насељу
    0.50
    endpush
    0.50
    новништво
    0.47
    ViewFeatures
    0.46
    świad
    0.43
    Exited
    0.43
    athione
    0.42
    чник
    0.41
     =======
    0.41
    Activations Density 3.219%

    No Known Activations