© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197381
    Prev
    Next
    INDEX
    Explanations

    Indian names and words

    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
    8
    1.03
    5
    0.95
    6
    0.94
    1
    0.91
    9
    0.86
    4
    0.85
    7
    0.82
    3
    0.76
    2
    0.75
    :
    0.66
    POSITIVE LOGITS
    م
    0.79
    ب
    0.76
    C
    0.74
    া
    0.71
    L
    0.67
    M
    0.66
    مي
    0.66
    它
    0.66
    ет
    0.64
    ه
    0.64
    Activations Density 0.000%

    No Known Activations