© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101820
    Prev
    Next
    INDEX
    Explanations

    uncomment to enable

    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_16_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
    ą
    0.55
    त्तियों
    0.53
     tespit
    0.52
     え
    0.50
    ètent
    0.50
    ᾗ
    0.49
     timepiece
    0.49
     pelot
    0.48
     plateforme
    0.48
    ྃ
    0.48
    POSITIVE LOGITS
    ncol
    0.59
    ويلة
    0.57
    conversion
    0.57
     خلال
    0.55
    er
    0.54
    perman
    0.54
    remainder
    0.54
    gene
    0.54
     conversion
    0.53
    riteria
    0.52
    Activations Density 0.001%

    No Known Activations