© 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. 18
    Prev
    Next
    INDEX
    Explanations

    Swedish place names and Swedish honorifics

    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
    UserScript
    -0.63
     jdbcTemplate
    -0.54
     EconPapers
    -0.54
    WebElementEntity
    -0.53
    GenerationType
    -0.51
     tačiau
    -0.51
     gynhyrchwyd
    -0.51
    المكان
    -0.51
    poel
    -0.51
     समीक्षक
    -0.50
    POSITIVE LOGITS
    pä
    0.51
    tät
    0.51
    colgroup
    0.51
     sinar
    0.46
    jär
    0.46
     uVar
    0.46
    GroupLayout
    0.45
    LY
    0.44
    kton
    0.44
    thay
    0.44
    Activations Density 2.475%

    No Known Activations