© 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. 1370
    Prev
    Next
    INDEX
    Explanations

    code or mark-up of web pages

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     
    -1.26
     loue
    -0.46
     gingival
    -0.46
     ſeveral
    -0.45
     juſt
    -0.43
     myſelf
    -0.43
     theſe
    -0.43
     Maximize
    -0.42
     Decorate
    -0.42
     canina
    -0.42
    POSITIVE LOGITS
    rungsseite
    0.82
    帖最后由
    0.81
    eqn
    0.73
    findpost
    0.70
    MigrationBuilder
    0.68
    posedge
    0.66
    +:+
    0.63
     AssemblyCulture
    0.61
    __':
    0.60
    AndEndTag
    0.59
    Activations Density 17.124%

    No Known Activations