© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259763
    Prev
    Next
    INDEX
    Explanations

    dataset loading or data handling

    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_22_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
     violated
    0.39
    すぐに
    0.38
    訲
    0.38
     violation
    0.38
     friday
    0.38
     jeweils
    0.37
    肯定是
    0.37
     sicuramente
    0.37
     dobl
    0.37
     pistola
    0.37
    POSITIVE LOGITS
     Diet
    0.46
     Cannabis
    0.45
     Curriculum
    0.44
     Supply
    0.44
    蕪
    0.42
     Spine
    0.41
     Sleep
    0.40
    ူး
    0.40
    筍
    0.40
     Qatar
    0.39
    Activations Density 0.000%

    No Known Activations