© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194246
    Prev
    Next
    INDEX
    Explanations

    formed by reduction supported RAM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seguir
    0.47
     मजबूत
    0.46
    統領
    0.46
    ధ్య
    0.45
    𝑻
    0.45
    FindingsResponse
    0.45
     வைத்த
    0.44
    ንዱ
    0.43
     piloto
    0.43
     igreja
    0.43
    POSITIVE LOGITS
    EN
    0.52
    =
    0.52
    Bi
    0.50
     Charcoal
    0.50
     charcoal
    0.50
     QTreeWidgetItem
    0.48
    in
    0.48
    Short
    0.48
    +=
    0.47
    IO
    0.47
    Activations Density 0.000%

    No Known Activations