© 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. 57815
    Prev
    Next
    INDEX
    Explanations

    fully utilize

    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
     мото
    0.54
     SURE
    0.51
     وحدة
    0.50
     примерно
    0.50
     герои
    0.49
    ະພັນ
    0.49
     motorbike
    0.46
    ^{+},
    0.46
     sailboat
    0.45
     constructs
    0.45
    POSITIVE LOGITS
    K
    0.72
    n
    0.59
    ม
    0.59
    <0x0D>
    0.58
    </u>
    0.57
    R
    0.56
    ส
    0.52
    S
    0.52
    斯
    0.52
    Mc
    0.51
    Activations Density 0.000%

    No Known Activations