© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87728
    Prev
    Next
    INDEX
    Explanations

    worst possible

    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
    ’
    0.76
     zenith
    0.66
     Prodig
    0.63
    ੇ
    0.61
     Wei
    0.61
     Burd
    0.61
    ى
    0.61
    gunakan
    0.58
     antigo
    0.58
    p
    0.57
    POSITIVE LOGITS
    <0xBE>
    0.64
    im
    0.62
    ING
    0.60
    면
    0.60
     породы
    0.60
    O
    0.60
    MS
    0.59
     at
    0.58
    ile
    0.58
     à
    0.58
    Activations Density 0.000%

    No Known Activations