© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65310
    Prev
    Next
    INDEX
    Explanations

    each

    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
    баров
    0.40
     Immutable
    0.38
    きれい
    0.37
     রোনাল
    0.37
    ద్య
    0.36
    㙅
    0.36
    ടുത്ത
    0.35
     نص
    0.35
    ásticas
    0.35
    >,</
    0.35
    POSITIVE LOGITS
    rous
    0.40
     seam
    0.40
     hvert
    0.40
    渕
    0.40
    bullets
    0.38
     triangles
    0.38
     eiusmod
    0.38
    illis
    0.38
    birds
    0.37
    cont
    0.37
    Activations Density 0.001%

    No Known Activations