© 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. 127414
    Prev
    Next
    INDEX
    Explanations

    gratuitous

    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
    ية
    0.86
    ب
    0.80
    на
    0.78
    تين
    0.67
     inférieure
    0.66
    ández
    0.66
    rás
    0.66
     расс
    0.64
     élevées
    0.64
    ت
    0.61
    POSITIVE LOGITS
    ze
    0.84
    man
    0.80
    or
    0.76
    world
    0.71
    ja
    0.70
    $
    0.70
    p
    0.67
     it
    0.67
    with
    0.66
    ir
    0.66
    Activations Density 0.001%

    No Known Activations