© 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. 61665
    Prev
    Next
    INDEX
    Explanations

    delirium tremens, Delaunay, deleterious

    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
    ۰
    1.70
     провер
    1.02
     сохра
    0.93
     воздей
    0.92
    llo
    0.91
    くまで
    0.87
    لے
    0.86
    েন
    0.85
    lng
    0.85
    lge
    0.84
    POSITIVE LOGITS
     on
    1.75
     to
    1.27
    ی
    1.20
    ک
    1.16
    та
    1.13
     from
    1.09
     with
    1.08
    1
    1.05
    ą
    1.04
    ut
    1.02
    Activations Density 0.000%

    No Known Activations