© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93534
    Prev
    Next
    INDEX
    Explanations

    continues to

    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_11_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
    ing
    0.84
    i
    0.79
    r
    0.75
    ization
    0.73
    z
    0.72
    ำ
    0.70
     vous
    0.68
    l
    0.67
    ig
    0.66
     p
    0.65
    POSITIVE LOGITS
    Kana
    0.64
    Parte
    0.63
    Color
    0.60
    Lip
    0.57
    Printing
    0.57
    朹
    0.57
    كي
    0.56
    Hasil
    0.56
    ARE
    0.56
    Heat
    0.55
    Activations Density 0.003%

    No Known Activations