© 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. 38247
    Prev
    Next
    INDEX
    Explanations

    white

    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
     i
    0.98
    е
    0.89
    о
    0.88
     be
    0.82
    ко
    0.77
     I
    0.76
    а
    0.72
    ли
    0.71
    换
    0.71
    كا
    0.69
    POSITIVE LOGITS
    ra
    0.90
    d
    0.85
    that
    0.80
    loss
    0.77
    list
    0.76
    که
    0.75
    lar
    0.73
    تها
    0.71
    Loss
    0.71
    u
    0.67
    Activations Density 0.015%

    No Known Activations