© 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. 108498
    Prev
    Next
    INDEX
    Explanations

    aisle, island

    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
    ى
    1.27
     d
    1.21
    (),
    1.21
    ים
    1.13
    ，
    1.10
    ے
    1.09
     l
    1.09
    3
    1.07
     g
    1.05
    $,
    1.05
    POSITIVE LOGITS
    t
    1.27
    n
    0.98
    f
    0.98
    nian
    0.95
    dW
    0.95
     pérd
    0.94
    dS
    0.93
     linéaires
    0.92
    fact
    0.92
    tional
    0.92
    Activations Density 0.001%

    No Known Activations