© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107358
    Prev
    Next
    INDEX
    Explanations

    convert data types

    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_2_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
    ри
    1.94
    ون
    1.78
    ä
    1.62
    á
    1.47
    ية
    1.33
    లు
    1.33
    ek
    1.31
    ामध्ये
    1.25
    ס
    1.22
    لی
    1.19
    POSITIVE LOGITS
    .
    1.13
    on
    1.05
    .}
    1.02
    let
    0.98
    К
    0.93
    শিকান্ত
    0.86
    '}
    0.85
    #.
    0.84
    for
    0.84
    phones
    0.82
    Activations Density 0.004%

    No Known Activations