© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123281
    Prev
    Next
    INDEX
    Explanations

    puzzle-solving

    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
    t
    1.00
    v
    0.98
    de
    0.87
     to
    0.71
    zr
    0.70
    ан
    0.69
    ni
    0.68
    tte
    0.68
    tR
    0.67
    tze
    0.66
    POSITIVE LOGITS
     avven
    0.60
     HMAC
    0.60
     allong
    0.58
    리
    0.58
     disting
    0.57
     veux
    0.57
     suddiv
    0.57
    しろ
    0.57
    는
    0.57
     buenos
    0.56
    Activations Density 0.001%

    No Known Activations