© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36179
    Prev
    Next
    INDEX
    Explanations

    Fast and Furious movie franchises

    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_11_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
    ?</
    0.57
    ?')
    0.54
    ાર્થના
    0.52
     GALL
    0.51
     দ্বারা
    0.48
    VERSION
    0.48
    arsanız
    0.48
    ガ
    0.48
    </h3>
    0.47
    ==============]
    0.47
    POSITIVE LOGITS
    í
    0.73
    le
    0.60
    f
    0.58
    io
    0.57
    Scope
    0.57
     К
    0.54
     разнообраз
    0.54
    id
    0.53
     amplo
    0.53
     seit
    0.52
    Activations Density 0.008%

    No Known Activations