© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131813
    Prev
    Next
    INDEX
    Explanations

    remove from air, heat, clot, weaker ones

    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
    f
    1.30
    з
    1.06
    א
    0.88
     Με
    0.88
     रहे
    0.86
     ו
    0.85
    c
    0.84
     अ
    0.82
    ada
    0.77
    cherry
    0.77
    POSITIVE LOGITS
    ní
    1.17
    with
    1.09
     with
    1.08
    to
    1.08
    2
    1.08
    níka
    1.06
     to
    0.99
    টি
    0.99
    ول
    0.98
    را
    0.96
    Activations Density 0.004%

    No Known Activations