© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218477
    Prev
    Next
    INDEX
    Explanations

    previously worked or served

    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
     earthenware
    0.38
     ro
    0.37
     kennis
    0.37
     ppt
    0.37
    ামান
    0.37
    рома
    0.36
    識
    0.36
    eware
    0.35
     właśnie
    0.35
    akn
    0.35
    POSITIVE LOGITS
    _\
    0.44
    ത്തിലുള്ള
    0.38
    でもある
    0.37
    젖
    0.35
     monoton
    0.35
    biased
    0.34
    立
    0.34
     biased
    0.33
    余裕
    0.33
     индекс
    0.33
    Activations Density 0.000%

    No Known Activations