© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17728
    Prev
    Next
    INDEX
    Explanations

    in the hands of

    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_40_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
    itamento
    0.38
     RP
    0.38
     rp
    0.36
    దీ
    0.35
    魃
    0.35
    档案馆
    0.34
    ogonal
    0.34
     `'\\
    0.34
    ieszka
    0.34
    γο
    0.33
    POSITIVE LOGITS
     hands
    1.54
    hands
    1.37
     Hands
    1.32
    Hands
    1.31
     tangan
    1.08
     руках
    1.04
     handen
    1.02
     हाथों
    1.01
     manos
    0.99
     mãos
    0.97
    Activations Density 0.037%

    No Known Activations