© 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. 201785
    Prev
    Next
    INDEX
    Explanations

    industry

    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
     निवडणुकी
    0.41
    ━━━━
    0.40
    istu
    0.39
     প্রয
    0.38
     สถาน
    0.37
     डिट
    0.37
     ಮಕ್ಕಳ
    0.37
    istel
    0.36
     印
    0.36
    neet
    0.36
    POSITIVE LOGITS
     grinder
    0.40
    ydın
    0.38
     leader
    0.38
    heimer
    0.37
    リード
    0.37
    WF
    0.37
    HEIM
    0.37
    ங்கி
    0.37
    Compliance
    0.36
     lãnh
    0.36
    Activations Density 0.000%

    No Known Activations