© 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. 39462
    Prev
    Next
    INDEX
    Explanations

    towns, booby traps, be used

    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
    ة
    1.02
    '
    1.01
    的
    0.98
    ين
    0.94
    ى
    0.79
    м
    0.77
    т
    0.73
    ер
    0.71
    ів
    0.71
    ко
    0.70
    POSITIVE LOGITS
    I
    0.82
     on
    0.80
     a
    0.70
     at
    0.69
    f
    0.67
    are
    0.65
    and
    0.64
    K
    0.63
     et
    0.62
    IA
    0.62
    Activations Density 0.013%

    No Known Activations