© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61916
    Prev
    Next
    INDEX
    Explanations

    program/programme

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     maqu
    0.41
     才
    0.41
     At
    0.39
     Set
    0.39
     частью
    0.39
     बिल्कुल
    0.38
     put
    0.37
     Garza
    0.37
    才会
    0.36
    才
    0.36
    POSITIVE LOGITS
     پروگرام
    0.49
     Nur
    0.47
     programma
    0.47
     NUR
    0.46
    programme
    0.46
     Programme
    0.44
     Verb
    0.44
    Programme
    0.44
    Developed
    0.43
     PRIOR
    0.43
    Activations Density 0.002%

    No Known Activations