© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239769
    Prev
    Next
    INDEX
    Explanations

    laundry care instructions and monadic bind

    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_25_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
     thoroughly
    0.38
     albeit
    0.37
     reducible
    0.37
    clinical
    0.35
     نوا
    0.35
    ט
    0.35
    センサー
    0.34
     asymptote
    0.34
    Atom
    0.34
    biggr
    0.34
    POSITIVE LOGITS
    лардын
    0.39
    против
    0.36
     accred
    0.36
    DFC
    0.36
    льский
    0.36
    ✘
    0.36
     Яндекс
    0.35
    மின்
    0.35
    ducted
    0.35
     Nope
    0.35
    Activations Density 0.000%

    No Known Activations