© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15201
    Prev
    Next
    INDEX
    Explanations

    labels, titles, and keywords often found in tables

    oai_token-act-pair · gemini-2.0-flash

    tables of data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     propOrder
    -0.56
    StateException
    -0.53
    stdc
    -0.47
    opot
    -0.44
    ędziesz
    -0.44
     سبورت
    -0.44
    onLoad
    -0.41
    έρα
    -0.41
    endregion
    -0.41
     Cassel
    -0.41
    POSITIVE LOGITS
    ########.
    0.79
    #+#
    0.68
     للاسماء
    0.59
    Билгалдахарш
    0.58
     оригіналу
    0.58
     lenker
    0.57
    #
    0.56
    InitVars
    0.56
     quinn
    0.54
    Життєпис
    0.54
    Activations Density 0.629%

    No Known Activations