© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8889
    Prev
    Next
    INDEX
    Explanations

    pygame.draw.rect

    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_40_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
    исленность
    0.40
    GR
    0.37
     DeL
    0.36
    Fetch
    0.36
    ATYPE
    0.35
    蘭
    0.34
    ANDEZ
    0.33
    itance
    0.33
     норма
    0.33
     গৃহ
    0.33
    POSITIVE LOGITS
    罡
    0.40
     promiscu
    0.36
     koost
    0.36
     yah
    0.34
     biased
    0.34
     रिव्यू
    0.33
    ۩
    0.33
     بینی
    0.33
     भट्ट
    0.32
     যৌ
    0.32
    Activations Density 0.003%

    No Known Activations