© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200432
    Prev
    Next
    INDEX
    Explanations

    predicting next word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    曉
    0.43
     भाषण
    0.41
     Earle
    0.39
    ridged
    0.39
     ಮಾತನಾಡ
    0.38
    Him
    0.38
    telefon
    0.37
    晓
    0.37
    ുവ
    0.36
     Akhtar
    0.36
    POSITIVE LOGITS
    rera
    0.41
    Furniture
    0.39
     stereotypes
    0.39
     Deformation
    0.39
     زیادی
    0.38
     कुश
    0.38
    Defaults
    0.38
    deformation
    0.38
    ciplinary
    0.38
    ]$,
    0.37
    Activations Density 0.006%

    No Known Activations