© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90314
    Prev
    Next
    INDEX
    Explanations

    G

    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_60_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
    -
    0.45
    U
    0.45
    ‌‌
    0.38
     ind
    0.37
     av
    0.37
     '"
    0.36
     ttk
    0.36
     u
    0.36
     repaid
    0.35
    L
    0.35
    POSITIVE LOGITS
    forKey
    0.43
    ofthe
    0.43
    លេខ
    0.39
    minsize
    0.39
    ]
    0.38
    bw
    0.38
     Andrey
    0.38
     ব্যয়ে
    0.38
     মন্
    0.37
    of
    0.37
    Activations Density 0.000%

    No Known Activations