© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12860
    Prev
    Next
    INDEX
    Explanations

    tables of numerical data, as indicated by the ampersands and percentage signs

    oai_token-act-pair · gemini-2.0-flash

    &

    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
     bezeichneter
    -0.76
    autique
    -0.69
    CppMethod
    -0.69
    featureID
    -0.69
    AccessorTable
    -0.67
    qrstuvwxyz
    -0.63
     Савезне
    -0.62
    complexContent
    -0.62
    vailable
    -0.60
     localObject
    -0.57
    POSITIVE LOGITS
    enumi
    0.53
     Himo
    0.52
    cised
    0.43
    ISupport
    0.42
     form
    0.41
    DIPSETTING
    0.41
     vòng
    0.40
    WithMany
    0.40
     lyk
    0.40
    TagMode
    0.40
    Activations Density 0.230%

    No Known Activations