© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215053
    Prev
    Next
    INDEX
    Explanations

    фа prefixes

    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_5_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
    いた
    1.25
     lulus
    1.06
     in
    1.05
    あ
    1.05
     수준
    1.02
     می‌شود
    0.98
    ᱘
    0.97
     possibilit
    0.96
     laborum
    0.94
    posición
    0.93
    POSITIVE LOGITS
    ри
    1.51
    v
    1.46
    ก
    1.44
    h
    1.37
    p
    1.36
    ю
    1.27
    n
    1.23
    m
    1.20
    ز
    1.20
    к
    1.19
    Activations Density 0.000%

    No Known Activations