© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180687
    Prev
    Next
    INDEX
    Explanations

    AS alias

    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_24_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
     sbag
    0.40
     대
    0.39
     errone
    0.39
     básicas
    0.37
     sylvis
    0.37
     සහිත
    0.37
     mennesker
    0.37
    错误
    0.36
     osoba
    0.36
     Glyph
    0.36
    POSITIVE LOGITS
    ܸ
    0.39
    venta
    0.38
    Iddict
    0.38
    ूं
    0.38
    Developer
    0.37
     spf
    0.37
     वारदात
    0.37
    ቛ
    0.36
     necessitated
    0.36
    ஆ
    0.36
    Activations Density 0.002%

    No Known Activations