© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129369
    Prev
    Next
    INDEX
    Explanations

    train

    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_1_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
    ’
    1.37
    on
    1.31
    il
    1.23
    are
    1.14
    ت
    1.11
    at
    1.09
    and
    1.05
    um
    1.02
    خ
    1.01
    ab
    0.99
    POSITIVE LOGITS
    <bos>
    1.00
    น
    0.96
    ş
    0.89
    }
    0.88
    ğini
    0.86
    ❘
    0.86
    ým
    0.84
     INTO
    0.83
    ние
    0.82
    iseries
    0.82
    Activations Density 0.001%

    No Known Activations