© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236410
    Prev
    Next
    INDEX
    Explanations

    based on

    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_32_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
    metall
    0.43
     রহস্য
    0.41
     pathology
    0.41
    鑒
    0.39
     환
    0.38
    ﺜ
    0.38
    тиву
    0.37
    Metall
    0.37
    ताव
    0.36
    Ⲃ
    0.36
    POSITIVE LOGITS
     Autres
    0.40
    openai
    0.39
     nasi
    0.37
    reter
    0.35
    ﻻ
    0.35
     sha
    0.35
     Guerr
    0.35
     soaking
    0.35
     fares
    0.34
     encar
    0.34
    Activations Density 0.008%

    No Known Activations