© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202067
    Prev
    Next
    INDEX
    Explanations

    historical authors and works

    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_12_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
    ('
    0.55
     tenho
    0.50
    非
    0.50
    s
    0.48
     emotion
    0.48
     poetry
    0.48
     innovation
    0.47
    (...
    0.46
     imaging
    0.46
    南
    0.46
    POSITIVE LOGITS
    ್ಟ
    0.57
    τού
    0.53
    ensure
    0.52
    cual
    0.50
    establish
    0.49
     Τ
    0.49
     asegur
    0.49
     Recuer
    0.49
     இந்ந
    0.49
     অনুষ্ঠানের
    0.48
    Activations Density 0.000%

    No Known Activations