© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133263
    Prev
    Next
    INDEX
    Explanations

    writing script

    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_6_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
     последствия
    1.03
     and
    1.00
    ระหว่าง
    0.95
     отношения
    0.95
     on
    0.94
    א
    0.92
    q
    0.91
     factores
    0.89
     sympa
    0.89
     órganos
    0.89
    POSITIVE LOGITS
    these
    1.05
    Khan
    0.97
    AL
    0.93
     Kön
    0.93
    the
    0.93
    that
    0.89
    cdots
    0.88
    })$
    0.85
    ON
    0.84
    this
    0.83
    Activations Density 0.001%

    No Known Activations