© 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. 157264
    Prev
    Next
    INDEX
    Explanations

    existence of

    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
    .
    0.91
    _
    0.88
    "
    0.81
    ek
    0.80
    '
    0.79
    ای
    0.77
    .&
    0.75
     vä
    0.74
    很
    0.74
    ala
    0.74
    POSITIVE LOGITS
    ל
    1.18
    л
    1.10
    ين
    1.01
    لها
    0.99
    a
    0.99
    यों
    0.95
    in
    0.95
    ar
    0.93
    ாக்கு
    0.92
    ls
    0.92
    Activations Density 0.001%

    No Known Activations