© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51656
    Prev
    Next
    INDEX
    Explanations

    legal terms

    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_55_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
     │
    0.45
    CHA
    0.40
     cha
    0.36
    лум
    0.34
    Xin
    0.34
     आलोचना
    0.34
    ostí
    0.34
     aceptas
    0.33
    ठमाडौं
    0.33
    roz
    0.33
    POSITIVE LOGITS
     Kies
    0.39
    })^{
    0.38
     Classical
    0.37
    hiti
    0.36
     થાય
    0.36
     Morse
    0.36
    hita
    0.36
     Males
    0.36
     Pers
    0.35
     unprepared
    0.35
    Activations Density 0.004%

    No Known Activations