© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31709
    Prev
    Next
    INDEX
    Explanations

    chat messages with roles

    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_31_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
     हेतु
    0.29
     glaube
    0.28
    ზე
    0.27
    აზე
    0.27
     घेण्यात
    0.27
     второй
    0.26
    }}\\
    0.26
    ቨ
    0.26
     Evaluation
    0.26
     هنتكلم
    0.26
    POSITIVE LOGITS
    PRESSURE
    0.28
    मु
    0.27
     vent
    0.27
    PROVIDER
    0.26
     VENT
    0.26
     وض
    0.26
    CAA
    0.25
    ለጠ
    0.25
    asks
    0.25
    Asked
    0.24
    Activations Density 0.001%

    No Known Activations