© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34666
    Prev
    Next
    INDEX
    Explanations

    ://

    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_50_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
    latent
    0.39
    -‘
    0.37
     சீ
    0.37
    -'
    0.35
     !!!!!
    0.35
     "_"
    0.34
    頓
    0.34
    aug
    0.34
    akata
    0.33
     अफेयर्स
    0.33
    POSITIVE LOGITS
     Oat
    0.35
    ffel
    0.35
     Hoff
    0.35
     거
    0.34
    Blanc
    0.34
    cious
    0.34
     মাদ
    0.34
     Hond
    0.34
     intercellular
    0.34
    Hits
    0.33
    Activations Density 0.001%

    No Known Activations