© 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. 197006
    Prev
    Next
    INDEX
    Explanations

    names and cultural words

    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
    غط
    0.41
    طة
    0.41
    берг
    0.40
     lab
    0.39
    гава
    0.39
     AVC
    0.38
    𝘿
    0.38
    лта
    0.38
    لط
    0.38
     galactose
    0.38
    POSITIVE LOGITS
     Ralf
    0.43
    slices
    0.39
    quasi
    0.38
    miques
    0.38
    idel
    0.37
    덩
    0.37
     Mars
    0.36
    信
    0.36
    qb
    0.36
     Moses
    0.35
    Activations Density 0.006%

    No Known Activations