© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125223
    Prev
    Next
    INDEX
    Explanations

    down payment

    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_3_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
     a
    0.82
    t
    0.78
    </h2>
    0.74
     as
    0.71
    ต์
    0.71
    p
    0.70
    ர்
    0.67
    טו
    0.65
    l
    0.65
    USE
    0.63
    POSITIVE LOGITS
    ación
    0.82
     eléctricos
    0.77
    alen
    0.75
    increased
    0.74
    ي
    0.72
    ations
    0.71
     trastornos
    0.70
    alin
    0.70
    \,\
    0.69
     மீது
    0.69
    Activations Density 0.010%

    No Known Activations