© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37625
    Prev
    Next
    INDEX
    Explanations

    Ujjayi, Udio

    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_3_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
    с
    0.96
    з
    0.96
    ס
    0.80
    س
    0.75
    d
    0.75
     to
    0.74
    drag
    0.73
    a
    0.73
    ス
    0.72
    u
    0.70
    POSITIVE LOGITS
    েন
    0.66
    owy
    0.66
    heon
    0.59
    িয়া
    0.58
    াক
    0.57
    িয়ে
    0.55
    owany
    0.55
    ো
    0.55
    leme
    0.55
    owane
    0.53
    Activations Density 0.003%

    No Known Activations