© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49552
    Prev
    Next
    INDEX
    Explanations

    code or technical jargon

    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_55_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
     six
    1.10
     Six
    1.09
    六
    1.03
    Six
    1.01
     सिक्स
    1.00
    six
    0.99
     šest
    0.98
     SIX
    0.98
    SIX
    0.95
     六
    0.94
    POSITIVE LOGITS
    ironolactone
    0.38
    MOUSE
    0.35
    HCM
    0.35
     xen
    0.34
     гор
    0.34
    plications
    0.34
     locality
    0.34
    idot
    0.34
     cluster
    0.33
     zwe
    0.33
    Activations Density 0.006%

    No Known Activations