© 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. 91127
    Prev
    Next
    INDEX
    Explanations

    `plt.figure(figsize=`

    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
    Fantasy
    0.56
    uttab
    0.56
     keç
    0.56
    hor
    0.55
    alış
    0.55
     वय
    0.54
    :
    0.54
    oths
    0.52
    läger
    0.52
     मनोवैज्ञानिक
    0.52
    POSITIVE LOGITS
     Estrella
    0.54
     molé
    0.53
     moléculas
    0.52
     hanno
    0.52
    稈
    0.52
     respal
    0.52
     Nodo
    0.52
     anunci
    0.51
     ResponseEntity
    0.51
     americanos
    0.51
    Activations Density 0.015%

    No Known Activations