© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206975
    Prev
    Next
    INDEX
    Explanations

    specific names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    French
    0.45
     Calhoun
    0.43
     loving
    0.43
    磷
    0.42
     French
    0.41
     Christensen
    0.40
     프랑
    0.38
     Loving
    0.38
    ྔ
    0.38
     জার্মান
    0.38
    POSITIVE LOGITS
    tester
    0.42
     ricotta
    0.42
     Yi
    0.41
     また
    0.37
    ेश्वर
    0.37
    Africa
    0.37
     ICA
    0.36
    Petra
    0.36
     INDIA
    0.36
    姿勢
    0.35
    Activations Density 0.007%

    No Known Activations