© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157801
    Prev
    Next
    INDEX
    Explanations

    wondrous items

    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_2_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
    ش
    1.23
    ب
    1.13
    σή
    1.02
    畛
    1.00
    に加え
    0.94
     영향을
    0.88
    ने
    0.87
     그다
    0.86
    ग्वि
    0.86
    기
    0.86
    POSITIVE LOGITS
    ল
    1.20
    ě
    1.15
    S
    1.05
    .
    1.04
    ى
    1.03
    L
    1.02
    е
    1.02
    м
    0.98
    т
    0.98
    렸
    0.97
    Activations Density 0.001%

    No Known Activations