© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 102
    Prev
    Next
    INDEX
    Explanations

    aqueous solution, gaseous atom, equity, cash

    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_40_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
    LIC
    0.40
     lelaki
    0.38
    olics
    0.38
     TURN
    0.38
    ┛
    0.37
    Lima
    0.36
     Transaction
    0.36
    тали
    0.35
    撚
    0.35
    TAC
    0.34
    POSITIVE LOGITS
     Rhe
    0.42
     Aqu
    0.41
    Aqu
    0.40
     aque
    0.39
     aqu
    0.38
     വെ
    0.38
     भूल
    0.38
     warmed
    0.37
    Rhe
    0.37
     Error
    0.37
    Activations Density 0.044%

    No Known Activations