© 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. 11417
    Prev
    Next
    INDEX
    Explanations

    error notes

    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
    ನ್ಸ್
    0.44
     CheckException
    0.41
    EOL
    0.41
     میکس
    0.41
     SKSpriteNode
    0.41
    KSpriteNode
    0.39
    ⌀
    0.39
    ➸
    0.39
    𝐾
    0.38
    Ⴌ
    0.38
    POSITIVE LOGITS
    Sus
    0.46
     offenders
    0.45
     Clock
    0.40
    Clock
    0.39
     handout
    0.39
     clock
    0.39
    Note
    0.39
     sus
    0.38
     offender
    0.38
     note
    0.37
    Activations Density 0.004%

    No Known Activations