© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159873
    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_2_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
    of
    0.80
    ad
    0.79
    ap
    0.71
    기
    0.68
    ش
    0.66
    iv
    0.64
    ove
    0.64
    ार्किक
    0.63
    mér
    0.63
    lés
    0.60
    POSITIVE LOGITS
    $
    0.95
     are
    0.94
    ра
    0.94
    ри
    0.88
    "
    0.86
    ро
    0.80
    ור
    0.80
    ί
    0.75
    :
    0.74
    6
    0.73
    Activations Density 0.000%

    No Known Activations