© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108648
    Prev
    Next
    INDEX
    Explanations

    GmbH or Haftung

    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_2_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
    ב
    1.27
    ని
    1.20
    נ
    1.18
    B
    1.15
    U
    1.13
    ول
    1.11
    其他
    1.09
    在
    1.09
    أ
    1.09
    り
    1.08
    POSITIVE LOGITS
    ן
    1.55
     are
    1.49
    ség
    1.11
    us
    1.08
     can
    1.01
    are
    1.00
    ing
    0.97
    ate
    0.95
    0
    0.94
    ses
    0.93
    Activations Density 0.000%

    No Known Activations