Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12028
    Prev
    Next
    INDEX
    Explanations

    descriptions of the mechanics of a linotype machine

    oai_token-act-pair · gemini-2.0-flash

    Guns and ammunition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    NameInMap
    -0.70
    jspx
    -0.66
    seamnă
    -0.65
    featureID
    -0.59
     rapporti
    -0.59
     تضيفلها
    -0.59
    encodeWith
    -0.57
    Diwedd
    -0.56
    uxxxx
    -0.55
    ::$_
    -0.54
    POSITIVE LOGITS
     MainAxisSize
    0.54
    nsec
    0.45
     belt
    0.44
    ComponentModel
    0.44
    SARS
    0.43
     flat
    0.43
    Belf
    0.42
    GC
    0.42
     خارجية
    0.41
     gas
    0.41
    Activations Density 0.976%

    No Known Activations