© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88282
    Prev
    Next
    INDEX
    Explanations

    boycott or stop

    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_23_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
    옳
    0.42
     насто
    0.41
     nessun
    0.39
     yık
    0.38
     regard
    0.38
     abdom
    0.37
    apte
    0.36
     потрі
    0.36
    ensk
    0.35
     argumento
    0.35
    POSITIVE LOGITS
     Fund
    0.37
    苍
    0.36
    —
    0.35
     Wildlife
    0.35
    EntityManager
    0.35
     அழக
    0.35
     Meteorological
    0.35
     ENT
    0.34
    เส้น
    0.34
    অন্য
    0.33
    Activations Density 0.004%

    No Known Activations