© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 79012
    Prev
    Next
    INDEX
    Explanations

    identifier or arn

    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
    ებს
    0.35
    ofsky
    0.35
    Reli
    0.34
    ("//
    0.34
     perpetuate
    0.34
     insulate
    0.33
     unlawfully
    0.33
     obscurity
    0.33
    шают
    0.33
     rely
    0.33
    POSITIVE LOGITS
    Pro
    0.36
    芭
    0.36
     Pro
    0.34
    贔
    0.34
    ℕ
    0.33
     caratter
    0.33
    garian
    0.33
     Liverpool
    0.32
    Australia
    0.32
    Liverpool
    0.32
    Activations Density 0.001%

    No Known Activations