© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228156
    Prev
    Next
    INDEX
    Explanations

    naked eye

    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_6_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
     ي
    1.14
    ция
    1.10
     في
    1.04
     اين
    0.99
    きます
    0.97
     если
    0.96
     де
    0.95
     zatim
    0.94
     и
    0.92
     وك
    0.92
    POSITIVE LOGITS
    ä
    1.40
    5
    1.27
    0
    1.25
    1
    1.22
    ud
    1.17
    EX
    1.17
    ang
    1.12
    ub
    1.11
    v
    1.11
    ur
    1.09
    Activations Density 0.000%

    No Known Activations