© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134111
    Prev
    Next
    INDEX
    Explanations

    Claritin

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Detector
    0.46
    Sixth
    0.43
    B
    0.41
     Gor
    0.40
    漓
    0.40
    letos
    0.39
     divisions
    0.39
     birdies
    0.38
    igos
    0.38
    धपुर
    0.38
    POSITIVE LOGITS
    ews
    0.37
     நில
    0.35
     бен
    0.35
     ▸
    0.34
    tutorial
    0.33
    трі
    0.33
     мело
    0.33
     हिंदी
    0.33
    ట్
    0.33
    ět
    0.33
    Activations Density 0.000%

    No Known Activations