© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86806
    Prev
    Next
    INDEX
    Explanations

    gap filling formulas

    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_3_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
    ка
    0.71
    ठीक
    0.66
    ोरा
    0.59
    こと
    0.59
    ۰
    0.57
    го
    0.54
    ो
    0.54
    に
    0.53
    ogaster
    0.52
    ].”
    0.52
    POSITIVE LOGITS
    s
    1.27
    ים
    0.99
    ς
    0.81
    ม
    0.76
    ني
    0.71
    \
    0.71
    ين
    0.66
    ור
    0.66
    ל
    0.65
     It
    0.64
    Activations Density 0.000%

    No Known Activations