© 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. 14098
    Prev
    Next
    INDEX
    Explanations

    text referencing a proportion or share of something

    oai_token-act-pair · gemini-2.0-flash

    majority

    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
    Autoritní
    -0.55
     '/':
    -0.52
     Redund
    -0.50
    IGraphics
    -0.49
     ['$
    -0.49
     hivat
    -0.48
     noastre
    -0.48
    #+#
    -0.46
     kategorii
    -0.45
    ensement
    -0.45
    POSITIVE LOGITS
     pinulongan
    0.68
    styleUrls
    0.62
    nium
    0.59
    AccessFile
    0.56
     parseFrom
    0.56
     NSCoder
    0.56
    mester
    0.54
    SequentialGroup
    0.54
    WebControls
    0.53
     متعلقه
    0.53
    Activations Density 1.719%

    No Known Activations