© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177661
    Prev
    Next
    INDEX
    Explanations

    time ranges

    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_29_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
    অর্চনা
    0.43
     stanje
    0.41
    يكية
    0.40
     Orte
    0.38
    假
    0.38
     बताएंगे
    0.38
    yczne
    0.38
     ciencias
    0.37
    द्योगिकी
    0.37
    授予
    0.37
    POSITIVE LOGITS
     pipes
    0.42
     kilograms
    0.39
     afternoon
    0.38
     composition
    0.37
     insulation
    0.37
    セ
    0.36
     ±
    0.36
     supervision
    0.35
     মন্ত্রী
    0.35
     axon
    0.34
    Activations Density 0.000%

    No Known Activations