© 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. 35213
    Prev
    Next
    INDEX
    Explanations

    We followed by action verb

    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
     unsol
    0.40
    క్
    0.39
     oblig
    0.39
     ష
    0.37
     uneas
    0.37
     compiler
    0.37
    Sham
    0.36
     sh
    0.36
     compilers
    0.36
     frustrated
    0.35
    POSITIVE LOGITS
     Potassium
    0.40
    ρακ
    0.38
     прока
    0.37
    钾
    0.36
     역할
    0.36
    pointing
    0.36
     잠
    0.35
     possession
    0.35
     potassium
    0.35
     звер
    0.35
    Activations Density 0.000%

    No Known Activations