© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39651
    Prev
    Next
    INDEX
    Explanations

    back 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_11_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
    m
    0.76
    ia
    0.68
    n
    0.67
    p
    0.61
    aa
    0.61
    aram
    0.60
    ore
    0.59
    ant
    0.57
    edition
    0.57
    y
    0.57
    POSITIVE LOGITS
    網友
    0.55
    л
    0.55
    тера
    0.53
     reagents
    0.53
    рку
    0.52
     noviembre
    0.50
    工艺
    0.50
     Wesleyan
    0.50
    מת
    0.50
     handset
    0.50
    Activations Density 0.002%

    No Known Activations