© 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. 228306
    Prev
    Next
    INDEX
    Explanations

    avocados

    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
    ，
    0.95
    اد
    0.91
    ى
    0.89
    da
    0.84
    ح
    0.84
    ،
    0.83
    كا
    0.82
    HEN
    0.79
    НА
    0.77
    РУ
    0.77
    POSITIVE LOGITS
    n
    1.35
    น
    0.96
    inen
    0.93
    রি
    0.91
    ล
    0.90
    하는
    0.85
    𝓲
    0.84
    cular
    0.83
    まし
    0.83
     planet
    0.82
    Activations Density 0.001%

    No Known Activations