© 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. 227375
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    u
    1.51
    0
    1.51
    т
    1.45
    is
    1.45
    et
    1.39
    it
    1.31
    ?
    1.27
    ت
    1.27
    ur
    1.25
    ся
    1.22
    POSITIVE LOGITS
     பதிலாக
    0.91
    даги
    0.89
    اکي
    0.86
     않는다
    0.82
    нің
    0.79
     في
    0.79
    ја
    0.79
    endDate
    0.79
    يرة
    0.78
    зульта
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.