© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197860
    Prev
    Next
    INDEX
    Explanations

    dread and variations

    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_9_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
    u
    1.18
    a
    1.15
    ه
    1.14
    y
    1.11
    e
    1.08
    ا
    1.04
    は
    1.04
    의
    1.02
     the
    1.01
    ي
    1.01
    POSITIVE LOGITS
    db
    0.92
    ta
    0.89
    ation
    0.87
    to
    0.86
    ene
    0.82
    ding
    0.82
     meandering
    0.81
    ti
    0.79
    di
    0.79
    td
    0.79
    Activations Density 0.001%

    No Known Activations