© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167761
    Prev
    Next
    INDEX
    Explanations

    save money

    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_56_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
     سا
    0.45
    Sign
    0.40
    Signature
    0.38
     الموقع
    0.37
    사
    0.37
    ellite
    0.37
    Signed
    0.36
    사인
    0.35
     سای
    0.34
     Saty
    0.34
    POSITIVE LOGITS
    セ
    2.28
     세
    2.19
    세
    2.03
    เซ
    2.00
     セ
    1.87
     เซ
    1.74
     safe
    1.72
     Се
    1.65
     સે
    1.59
    safe
    1.56
    Activations Density 0.012%

    No Known Activations