© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103403
    Prev
    Next
    INDEX
    Explanations

    kayaking activity

    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_1_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
     be
    1.97
     to
    1.92
     y
    1.52
     on
    1.52
     at
    1.52
     as
    1.48
     by
    1.42
     has
    1.42
    0
    1.41
     e
    1.38
    POSITIVE LOGITS
     núcle
    1.12
    т
    1.07
    un
    1.06
     اکثریت
    1.05
     únicamente
    1.04
    ﺎ
    1.04
    ामध्ये
    1.02
    arów
    1.01
    diği
    1.00
     činjen
    1.00
    Activations Density 0.000%

    No Known Activations