© 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. 8972
    Prev
    Next
    INDEX
    Explanations

    descriptions of people's jobs or roles they held.

    oai_token-act-pair · 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
    ècie
    -0.54
    发表于
    -0.54
    ternut
    -0.50
    Przypisy
    -0.48
     للاسماء
    -0.48
    begingroup
    -0.47
    Референце
    -0.47
    Speaker
    -0.47
    Chair
    -0.45
     AssemblyCulture
    -0.45
    POSITIVE LOGITS
     GoogleFonts
    0.53
     المعيارى
    0.52
    tagext
    0.52
    .*")]
    0.51
    NgModule
    0.49
    BASEPATH
    0.48
    Autoritní
    0.47
    BagConstraints
    0.46
    worpen
    0.46
     BoxDecoration
    0.45
    Activations Density 9.361%

    No Known Activations