© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12227
    Prev
    Next
    INDEX
    Explanations

    words related to business services and companies

    oai_token-act-pair · gemini-2.0-flash

    coding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    saraba
    -0.63
     form
    -0.48
     tartalomajánló
    -0.47
    __.__
    -0.47
    form
    -0.47
    IContainer
    -0.45
    ScopeManager
    -0.45
    PHeader
    -0.45
     koja
    -0.44
    Personendaten
    -0.43
    POSITIVE LOGITS
    enumi
    0.80
     BrowserModule
    0.62
     MediatR
    0.61
     InputDecoration
    0.60
    migrationBuilder
    0.57
    rxjs
    0.57
    orsese
    0.55
     مفص
    0.53
     kreatif
    0.52
    EJB
    0.52
    Activations Density 8.180%

    No Known Activations