© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36442
    Prev
    Next
    INDEX
    Explanations

    typical followed by context

    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
    ARA
    0.71
    К
    0.70
    akkhati
    0.70
     আওতায়
    0.67
    boiled
    0.67
    يكل
    0.66
    awesi
    0.66
    INV
    0.64
    kiyor
    0.64
    waters
    0.63
    POSITIVE LOGITS
    ↵↵
    0.82
     repent
    0.62
     mislead
    0.59
     violin
    0.58
    ↵
    0.58
     gobern
    0.58
      
    0.57
     $
    0.57
     gestion
    0.57
     jeopard
    0.55
    Activations Density 0.006%

    No Known Activations