© 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. 201475
    Prev
    Next
    INDEX
    Explanations

    base material substrate

    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
     as
    1.30
    ق
    1.20
    (
    1.17
    ^
    1.12
    ↵↵
    1.02
    ف
    1.00
    ;
    0.98
    ்ப
    0.97
    0.95
          
    0.94
    POSITIVE LOGITS
    n
    1.11
    vorm
    1.02
    t
    1.01
    nál
    0.99
    сион
    0.98
    inį
    0.97
    screen
    0.96
    щен
    0.95
    sodium
    0.92
    elijke
    0.91
    Activations Density 0.000%

    No Known Activations