© 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. 83
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets and Russian words

    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
     Houſe
    -0.15
    leſs
    -0.14
    ſelf
    -0.10
     Jefus
    -0.08
    ſelves
    -0.08
     itſelf
    -0.08
     Theſe
    -0.07
    wiſe
    -0.05
    neſs
    -0.05
    ^(@)
    -0.04
    POSITIVE LOGITS
    MigrationBuilder
    1.40
     saites
    1.33
     Chwiliwch
    1.28
    oa̍t
    1.27
     مرئيه
    1.24
    tagHelperRunner
    1.23
     للاسماء
    1.20
     EconPapers
    1.19
     المعيارى
    1.19
     مشين
    1.16
    Activations Density 11.042%

    No Known Activations