© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87161
    Prev
    Next
    INDEX
    Explanations

    core value proposition

    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_3_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
    an
    0.78
    i
    0.73
    ر
    0.62
    r
    0.61
    er
    0.59
    DeathRecord
    0.55
    ták
    0.55
    enstein
    0.54
    e
    0.54
    iov
    0.54
    POSITIVE LOGITS
    ری
    0.86
    یت
    0.84
    )$,
    0.82
     to
    0.79
    یس
    0.76
    pengaruhi
    0.70
    а
    0.70
    ف
    0.69
    רי
    0.68
     risques
    0.68
    Activations Density 0.015%

    No Known Activations