© 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. 132392
    Prev
    Next
    INDEX
    Explanations

    say

    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
    vide
    0.39
    br
    0.39
    Ра
    0.38
    Vide
    0.38
    🇩
    0.38
     vide
    0.38
    Fun
    0.38
    ском
    0.38
     Dinesh
    0.37
    ್ಯೂ
    0.37
    POSITIVE LOGITS
    Ⴚ
    0.41
    ടുത്ത
    0.40
    hren
    0.38
     Pater
    0.38
     substitutional
    0.38
    Cabin
    0.37
    ahs
    0.37
     renin
    0.36
    敞
    0.36
     Cabin
    0.36
    Activations Density 0.001%

    No Known Activations