© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98473
    Prev
    Next
    INDEX
    Explanations

    scheduling tasks

    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_14_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
    ла
    0.63
    A
    0.58
    number
    0.57
    De
    0.57
    <0xBC>
    0.56
    *
    0.55
    '
    0.54
    At
    0.52
    with
    0.52
    Сан
    0.52
    POSITIVE LOGITS
     avocat
    0.69
     ጥሩ
    0.65
     neoc
    0.64
     therapist
    0.61
     mania
    0.61
     persona
    0.60
     lover
    0.60
     नायक
    0.59
     ശക്ത
    0.59
     här
    0.59
    Activations Density 0.001%

    No Known Activations