© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56915
    Prev
    Next
    INDEX
    Explanations

    boardwalk

    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_11_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
    通过
    0.50
    𝗝
    0.49
    0.48
    ᅴ
    0.48
    ⴼ
    0.46
    Year
    0.46
    Ocean
    0.45
    Iris
    0.44
    ؟
    0.44
    Спасибо
    0.43
    POSITIVE LOGITS
    ла
    0.52
     குடும்ப
    0.50
     என்னை
    0.50
     मुझ
    0.49
    é
    0.48
     eine
    0.47
    гато
    0.46
    மான்
    0.46
    welt
    0.46
     Maharashtra
    0.46
    Activations Density 0.000%

    No Known Activations