© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45265
    Prev
    Next
    INDEX
    Explanations

    if so,

    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_22_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
     addBook
    0.43
     laminar
    0.40
    )~
    0.40
    archiviato
    0.40
     insofar
    0.39
    FON
    0.39
     trailbl
    0.39
     සිය
    0.39
     neko
    0.38
     Jika
    0.38
    POSITIVE LOGITS
    g
    0.42
    uary
    0.40
    毁灭
    0.40
    คุณ
    0.39
    (".")
    0.39
    usis
    0.38
    ("
    0.38
    何を
    0.38
     راز
    0.37
     گ
    0.37
    Activations Density 0.003%

    No Known Activations