© 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. 3442
    Prev
    Next
    INDEX
    Explanations

    mentions of change in quantity, size, or magnitude.

    oai_token-act-pair · gemini-2.0-flash

    numbers and quantities

    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
    seteq
    -0.43
     butterknife
    -0.42
    Портал
    -0.41
    Medium
    -0.41
    medium
    -0.41
    Geplaatst
    -0.40
     Medium
    -0.40
     medium
    -0.39
    colta
    -0.39
     Процитовано
    -0.39
    POSITIVE LOGITS
     threefold
    0.94
     thrice
    0.93
     times
    0.92
     orders
    0.92
     twice
    0.91
     TIMES
    0.88
     Twice
    0.84
     BoxFit
    0.82
    twice
    0.81
    kháu
    0.81
    Activations Density 2.486%

    No Known Activations