© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37450
    Prev
    Next
    INDEX
    Explanations

    Rider

    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_11_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
    υ
    0.56
     were
    0.54
     bindings
    0.51
     exception
    0.50
    Sel
    0.50
     PEAR
    0.50
    ro
    0.49
    </i>
    0.49
    Α
    0.49
    วม
    0.48
    POSITIVE LOGITS
    oju
    0.55
    هههه
    0.55
     ஆகும்
    0.54
     MDLVertex
    0.54
    លេ
    0.54
    oying
    0.54
     spicy
    0.53
    klin
    0.53
    ajero
    0.53
     dolayı
    0.53
    Activations Density 0.000%

    No Known Activations