© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124268
    Prev
    Next
    INDEX
    Explanations

    persistence

    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_37_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
    rez
    0.39
    榨
    0.38
    ifício
    0.36
    ITIES
    0.36
    டிப்பு
    0.36
    chloride
    0.35
    焲
    0.35
    isHidden
    0.35
    Dougall
    0.34
    Detectable
    0.34
    POSITIVE LOGITS
     tk
    0.44
    tong
    0.42
    cdr
    0.39
     dzie
    0.38
     తయారు
    0.38
     greets
    0.37
    涟
    0.37
     hala
    0.37
    elwv
    0.36
     od
    0.35
    Activations Density 0.003%

    No Known Activations