© 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. 218930
    Prev
    Next
    INDEX
    Explanations

    conditions and agreements

    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
     colleg
    0.37
    കാല
    0.36
    jumping
    0.36
    ทด
    0.36
    ؑ
    0.35
     instanceof
    0.34
     계
    0.33
     испыта
    0.33
     জুল
    0.33
     multipart
    0.33
    POSITIVE LOGITS
     expl
    0.43
    mış
    0.39
    expl
    0.38
     predictable
    0.35
    ">•
    0.35
     satisfied
    0.35
     Ikea
    0.35
     urea
    0.34
    ებას
    0.34
    膈
    0.34
    Activations Density 0.000%

    No Known Activations