© 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. 8933
    Prev
    Next
    INDEX
    Explanations

    followed by a question or possibility

    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
     ask
    1.73
     Ask
    1.55
    Ask
    1.49
    ask
    1.46
     ASK
    1.19
    ASK
    1.16
    问
    1.12
     try
    1.10
     asks
    1.09
    問
    1.07
    POSITIVE LOGITS
     could
    1.38
     Could
    1.34
    Could
    1.31
    could
    1.30
     могла
    1.20
     COULD
    1.15
     könnte
    1.13
     мог
    1.12
     pourrait
    1.11
     podría
    1.10
    Activations Density 0.168%

    No Known Activations