© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8910
    Prev
    Next
    INDEX
    Explanations

    prefixes 'co-', 'hydro-', 'electro-', 'ob-', 'bo-' and 'fo-'

    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
    PerformLayout
    -0.62
    TagMode
    -0.61
    men
    -0.57
    tours
    -0.56
    帖最后由
    -0.55
    ValueStyle
    -0.54
    t
    -0.54
     jsPsych
    -0.53
    mans
    -0.52
    l
    -0.52
    POSITIVE LOGITS
    yee
    0.48
    sex
    0.48
    yer
    0.47
    kk
    0.46
    yl
    0.46
    ki
    0.45
    lecular
    0.45
    ebi
    0.43
    kok
    0.43
    seb
    0.43
    Activations Density 3.051%

    No Known Activations