© 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. 127600
    Prev
    Next
    INDEX
    Explanations

    foreign words and names

    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
    larni
    0.61
    broccoli
    0.57
    苖
    0.55
    painted
    0.54
    等于
    0.54
    spouse
    0.53
     дату
    0.53
    precipitation
    0.53
    menuCategory
    0.52
    membre
    0.52
    POSITIVE LOGITS
    ?
    0.71
    ش
    0.63
     I
    0.62
    !
    0.62
    L
    0.62
    N
    0.61
    ering
    0.60
    ah
    0.59
    R
    0.59
    ر
    0.59
    Activations Density 0.000%

    No Known Activations