© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6486
    Prev
    Next
    INDEX
    Explanations

    technical decisions making

    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
     investimento
    0.28
     structuring
    0.27
    Structuring
    0.27
     strukt
    0.26
    PublicKey
    0.26
     nChar
    0.26
    struktur
    0.25
    ,*/}
    0.25
     भग्न
    0.25
     PublicKey
    0.25
    POSITIVE LOGITS
     decided
    0.43
     decisions
    0.42
     Decisions
    0.41
     decision
    0.39
     Decision
    0.36
     decides
    0.36
    Decision
    0.36
     decid
    0.34
     keputusan
    0.34
     deciding
    0.33
    Activations Density 0.033%

    No Known Activations