© 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. 16913
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    }^{-}
    0.41
     resampling
    0.39
     []
    0.39
     {}
    0.39
     perceptions
    0.37
     ⠀
    0.37
     {})
    0.36
     conserve
    0.35
     scho
    0.35
     احتجاج
    0.35
    POSITIVE LOGITS
     zero
    1.43
    zero
    1.25
     zéro
    1.24
    Zero
    1.20
     Zero
    1.20
     ZERO
    1.18
    零
    1.16
     जीरो
    1.12
     cero
    1.10
     صفر
    1.07
    Activations Density 0.093%

    No Known Activations