© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56798
    Prev
    Next
    INDEX
    Explanations

    slow or gradual progression

    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_11_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
    '
    0.84
     a
    0.66
    a
    0.64
     control
    0.63
    ’
    0.61
     dependents
    0.58
     defin
    0.57
     compar
    0.55
     brin
    0.55
     the
    0.54
    POSITIVE LOGITS
    드
    0.71
    ка
    0.63
    মেন্ট
    0.60
    ουσ
    0.58
     Diakses
    0.57
    Receipt
    0.57
    ರ್ಮ
    0.57
     Labrenzia
    0.56
    Alph
    0.56
    $}
    0.56
    Activations Density 0.000%

    No Known Activations