© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48969
    Prev
    Next
    INDEX
    Explanations

    medical license or specialized registration

    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_31_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
     T
    0.36
     piet
    0.30
     shirts
    0.30
     Ss
    0.30
    SIB
    0.29
    取材
    0.29
     未
    0.29
    TextField
    0.29
     zindagi
    0.29
     Alley
    0.29
    POSITIVE LOGITS
    枠
    0.38
     रुख
    0.36
     transl
    0.34
     Mittel
    0.34
    Bước
    0.33
     Prozess
    0.33
    Transl
    0.33
     passo
    0.32
    calcul
    0.32
     szczegól
    0.32
    Activations Density 0.000%

    No Known Activations