© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46703
    Prev
    Next
    INDEX
    Explanations

    stopping or prevention

    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_3_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
    ية
    0.82
    '
    0.70
     искусства
    0.68
    ๑
    0.64
    ',
    0.63
    OP
    0.63
     can
    0.60
    ود
    0.58
    ین
    0.57
     attham
    0.57
    POSITIVE LOGITS
    on
    0.84
    of
    0.71
    al
    0.68
    一样
    0.68
    the
    0.66
    d
    0.65
    u
    0.63
    onik
    0.63
    en
    0.61
    త
    0.61
    Activations Density 0.006%

    No Known Activations