© 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. 231293
    Prev
    Next
    INDEX
    Explanations

    pcs

    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
    К
    0.66
    </strong>
    0.60
    س
    0.58
    ó
    0.58
    É
    0.55
    '],
    0.54
    <0x0D>
    0.54
    ב
    0.54
    ف
    0.52
    З
    0.52
    POSITIVE LOGITS
    inį
    0.47
    erweise
    0.45
    thet
    0.45
    রন
    0.45
    legt
    0.44
    लट
    0.44
    ᆹ
    0.43
     मागणी
    0.43
    ljivo
    0.42
    зыва
    0.42
    Activations Density 0.000%

    No Known Activations