© 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. 4094
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations, countries, and positions of authority.

    oai_token-act-pair · gemini-2.0-flash

    ArgsConstructor

    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
    abestanden
    -0.63
     Wiktionnaire
    -0.59
    Rüyada
    -0.58
    fjspx
    -0.58
    ParallelGroup
    -0.56
     nahilalakip
    -0.56
    CodedInputStream
    -0.56
    aderie
    -0.55
    athione
    -0.54
    rouvez
    -0.54
    POSITIVE LOGITS
    ArgsConstructor
    0.57
    ANTLR
    0.54
     ModelExpression
    0.52
     noqa
    0.50
    ritsar
    0.49
     defaultstate
    0.48
    ClCompile
    0.47
     Miami
    0.47
    adaptiveStyles
    0.47
    Dallas
    0.47
    Activations Density 3.883%

    No Known Activations