© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126923
    Prev
    Next
    INDEX
    Explanations

    the best part

    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
    rekken
    0.70
    ↵
    0.68
    larda
    0.68
    मधून
    0.67
    ре
    0.66
    ει
    0.64
    t
    0.63
    lari
    0.63
     CWE
    0.62
    cích
    0.62
    POSITIVE LOGITS
    н
    0.78
    of
    0.76
    க்
    0.72
    ם
    0.72
    IN
    0.70
     przyczyn
    0.68
     вже
    0.68
    ס
    0.67
    ຂອງ
    0.66
     участие
    0.64
    Activations Density 0.001%

    No Known Activations