© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227612
    Prev
    Next
    INDEX
    Explanations

    az and tokens from various languages

    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_6_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
    ↵
    1.27
     to
    1.24
    ↵↵
    0.98
     that
    0.93
     dislocations
    0.93
    ь
    0.90
    3
    0.84
    ス
    0.84
     on
    0.82
     conson
    0.82
    POSITIVE LOGITS
    at
    1.24
    er
    1.20
    ar
    1.08
    il
    1.06
    ol
    1.06
    em
    1.03
    െല്ലാം
    1.02
    an
    1.00
    u
    0.98
    ov
    0.97
    Activations Density 0.000%

    No Known Activations