© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142562
    Prev
    Next
    INDEX
    Explanations

    perfecting words

    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_0_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
    ется
    1.52
    ación
    1.48
    ך
    1.30
    ール
    1.30
    èg
    1.20
    ида
    1.20
    и
    1.16
    ᱗
    1.16
     смесь
    1.14
    кие
    1.13
    POSITIVE LOGITS
    d
    1.94
    e
    1.92
    n
    1.84
    v
    1.77
    ;
    1.76
    The
    1.71
    W
    1.71
    B
    1.70
    P
    1.65
    S
    1.63
    Activations Density 0.000%

    No Known Activations