© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11714
    Prev
    Next
    INDEX
    Explanations

    words that suggest a preceding event or time

    oai_token-act-pair · gemini-2.0-flash

    earlier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.16
     autorytatywna
    -0.84
     InputDecoration
    -0.65
    attendre
    -0.62
    />";
    -0.61
     متعلقه
    -0.59
    +#+
    -0.59
     باخ
    -0.58
     my
    -0.58
     lot
    -0.57
    POSITIVE LOGITS
     acquaintance
    0.62
    mallows
    0.61
     édition
    0.56
    PageFactory
    0.55
     intruder
    0.54
     endowment
    0.54
     indigenous
    0.53
    ACLE
    0.53
     Andalu
    0.52
     entreprise
    0.52
    Activations Density 1.654%

    No Known Activations