© 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. 166243
    Prev
    Next
    INDEX
    Explanations

    python

    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
     Browning
    0.37
     LOCATION
    0.36
    ambo
    0.36
     WITH
    0.36
    ట్స్‌
    0.36
    patri
    0.36
     Cet
    0.35
    瑯
    0.35
     राजवंश
    0.35
     Monarch
    0.34
    POSITIVE LOGITS
     остав
    0.42
    zeczy
    0.40
     وسلم
    0.38
     wieku
    0.37
    成り立つ
    0.37
    DeviceCompliance
    0.36
     stimulates
    0.36
     прогре
    0.36
    ڈیو
    0.36
     چپ
    0.35
    Activations Density 0.001%

    No Known Activations