© 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. 9877
    Prev
    Next
    INDEX
    Explanations

    image credits and copyright information

    oai_token-act-pair · gemini-2.0-flash

    photos and tribune

    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
     et
    -0.52
    softc
    -0.50
    échelle
    -0.47
    APB
    -0.46
     al
    -0.46
     presentato
    -0.45
    aglia
    -0.45
    чник
    -0.44
    <eos>
    -0.43
    uy
    -0.43
    POSITIVE LOGITS
    webElementXpaths
    0.77
    UnusedPrivate
    0.73
    FormTagHelper
    0.70
    AddTagHelper
    0.68
    httphttps
    0.67
    Personendaten
    0.67
    InvalidProtocol
    0.65
     referrerpolicy
    0.65
     ContentValues
    0.65
     raiſ
    0.61
    Activations Density 1.544%

    No Known Activations