© 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. 6637
    Prev
    Next
    INDEX
    Explanations

    snippets of code, potentially with annotations or comments

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
     harmonic
    -0.92
     Hawkins
    -0.86
     Harmon
    -0.85
     Harmonic
    -0.85
     Harwood
    -0.84
     homology
    -0.84
     handler
    -0.84
     Handler
    -0.82
    Hol
    -0.82
     Hamilton
    -0.81
    POSITIVE LOGITS
    AlterField
    0.47
    yszcz
    0.43
    zionata
    0.41
    setCellValue
    0.41
    cination
    0.40
    ftagPool
    0.39
     وتسجيلات
    0.38
    minY
    0.38
    scrapy
    0.37
     Affiliations
    0.35
    Activations Density 2.322%

    No Known Activations