© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218868
    Prev
    Next
    INDEX
    Explanations

    just announced/released

    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
    Career
    0.37
     career
    0.36
    Seine
    0.36
     lun
    0.35
    wak
    0.34
    俩
    0.34
    瑋
    0.33
    Lett
    0.33
    dims
    0.33
    impress
    0.33
    POSITIVE LOGITS
     mất
    0.41
     ní
    0.39
     Montevideo
    0.37
     заб
    0.36
    陪伴
    0.36
     bordering
    0.36
     headlines
    0.35
     NEVER
    0.35
    urés
    0.35
    昃
    0.35
    Activations Density 0.000%

    No Known Activations