© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111863
    Prev
    Next
    INDEX
    Explanations

    Corfu Town

    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_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
    ’
    1.55
     to
    1.23
    -
    1.13
     dependence
    1.04
     requisite
    1.00
     responsiveness
    0.97
     disapproved
    0.95
     symptomatic
    0.94
     predisposition
    0.93
    pered
    0.93
    POSITIVE LOGITS
    a
    1.84
    ي
    1.80
    i
    1.58
    ات
    1.49
    m
    1.44
    f
    1.42
    ف
    1.42
    e
    1.41
    s
    1.41
    as
    1.37
    Activations Density 0.000%

    No Known Activations