© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2765
    Prev
    Next
    INDEX
    Explanations

    gerunds followed by prepositions

    oai_token-act-pair · gemini-2.0-flash

    high-action scenarios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Controllo
    -0.65
    ArgsConstructor
    -0.61
    ftagPool
    -0.60
    ModelBuilder
    -0.59
    <bos>
    -0.58
     gehouden
    -0.56
    IContainer
    -0.56
    χρι
    -0.54
    rália
    -0.54
    ,:);
    -0.54
    POSITIVE LOGITS
     Reſ
    0.59
    onOptions
    0.56
    ativní
    0.55
    findpost
    0.54
    uxxxx
    0.50
    RTEX
    0.49
     Majefty
    0.49
    ISupport
    0.48
     driving
    0.47
    imah
    0.47
    Activations Density 0.864%

    No Known Activations