© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28233
    Prev
    Next
    INDEX
    Explanations

    publicly available

    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
    intis
    0.35
    江南
    0.35
     Ausland
    0.34
     komple
    0.34
    ivere
    0.34
    矯
    0.33
    ̫
    0.33
    ដើ
    0.33
     اسرائی
    0.33
    দূ
    0.33
    POSITIVE LOGITS
     publicly
    2.75
    公开
    2.34
     public
    2.20
    公開
    2.19
     공개
    2.19
     публи
    2.03
     öffentlich
    2.02
    public
    1.99
     offent
    1.93
     सार्वजनिक
    1.90
    Activations Density 0.379%

    No Known Activations