© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21264
    Prev
    Next
    INDEX
    Explanations

    run

    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_56_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
     বৎস
    0.38
    婁
    0.37
     outflow
    0.36
     cms
    0.36
    colFirst
    0.35
     丶
    0.35
    *:
    0.35
     Them
    0.35
    留
    0.35
     springs
    0.34
    POSITIVE LOGITS
     re
    0.66
    Run
    0.52
     vaj
    0.49
     Re
    0.45
    run
    0.45
    مره
    0.45
     run
    0.45
    مرة
    0.43
    Re
    0.42
    חק
    0.40
    Activations Density 0.002%

    No Known Activations