© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146166
    Prev
    Next
    INDEX
    Explanations

    return

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     dev
    1.63
     반
    1.28
    dev
    1.14
     Dev
    1.09
    Dev
    1.06
    반
    0.98
    ito
    0.95
    半
    0.88
     Half
    0.83
     half
    0.82
    POSITIVE LOGITS
    Returned
    0.86
     Returned
    0.82
    returned
    0.82
    Returns
    0.80
     returned
    0.79
     Returns
    0.79
     returns
    0.78
    返回
    0.78
     返回
    0.72
    returns
    0.70
    Activations Density 0.000%

    No Known Activations