© 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. 75450
    Prev
    Next
    INDEX
    Explanations

    plan structure or outline

    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
    employee
    0.38
     interviewer
    0.38
     oed
    0.37
    形状
    0.37
     sauté
    0.36
     tribulations
    0.36
    Bt
    0.36
    填
    0.35
     conditioner
    0.35
    ээ
    0.35
    POSITIVE LOGITS
     Plan
    0.44
     Dokument
    0.43
     Submission
    0.41
    計劃
    0.41
    Plan
    0.40
     документів
    0.40
     dokumen
    0.40
     document
    0.40
    计划
    0.38
     Appendix
    0.38
    Activations Density 0.130%

    No Known Activations