© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134395
    Prev
    Next
    INDEX
    Explanations

    zodiac Landings

    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
    性
    1.31
    s
    1.23
    ترین
    1.13
    dt
    1.05
    u
    1.03
    df
    1.02
    大
    1.02
    ка
    0.98
    wrap
    0.94
    ್ಯ
    0.93
    POSITIVE LOGITS
    '
    1.87
    н
    1.36
    น
    1.32
    ي
    1.10
    ığı
    1.09
    h
    1.01
    hala
    1.00
    ক
    1.00
    นด์
    0.99
    м
    0.98
    Activations Density 0.000%

    No Known Activations