© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107190
    Prev
    Next
    INDEX
    Explanations

    Penrose stairs, tiles, Renard

    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_1_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
    ;
    1.19
    า
    1.13
    u
    1.06
    ン
    1.06
    아
    1.05
    ки
    1.04
    ла
    1.03
    다
    1.00
    ना
    0.99
    nél
    0.98
    POSITIVE LOGITS
    amento
    0.92
    ாவில்
    0.88
    avan
    0.86
    ியை
    0.86
    嵬
    0.86
    avez
    0.84
    ாகு
    0.83
    inement
    0.82
    ூர்
    0.80
     don
    0.79
    Activations Density 0.000%

    No Known Activations