© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206780
    Prev
    Next
    INDEX
    Explanations

    unravelMethod Used: 1Reason: MAX_ACTIVATING_TOKENS are variations of 'unravel' or 'uncover'

    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_46_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
    GEST
    0.39
    ärsk
    0.38
     الصغيرة
    0.38
     βρί
    0.36
    urst
    0.35
    rrh
    0.35
    的小
    0.35
    
    0.34
     pequeño
    0.34
    옳
    0.34
    POSITIVE LOGITS
     Laur
    0.42
     Flames
    0.42
     understandings
    0.38
    нике
    0.37
     sekret
    0.36
    ские
    0.36
     Ny
    0.36
    秘书
    0.36
     parte
    0.35
     Belg
    0.35
    Activations Density 0.003%

    No Known Activations