© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31944
    Prev
    Next
    INDEX
    Explanations

    I

    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
    ʲ
    0.41
     watert
    0.38
    Ска
    0.38
    봐
    0.35
    зумі
    0.35
     hard
    0.35
    МИ
    0.34
     fini
    0.34
     OCA
    0.34
    ဆ
    0.34
    POSITIVE LOGITS
     garam
    0.48
     एन
    0.43
    لاء
    0.38
    тяну
    0.38
    ety
    0.37
     Gar
    0.37
    ρκ
    0.37
    unis
    0.37
     garantie
    0.37
    튠
    0.36
    Activations Density 0.008%

    No Known Activations