© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52383
    Prev
    Next
    INDEX
    Explanations

    flow and stream concepts

    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_30_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
    рованной
    0.38
    Atlant
    0.36
    colon
    0.36
     धर्मेंद्र
    0.36
    ılmış
    0.35
    百科
    0.35
     വേദിക
    0.35
    装
    0.34
    褰
    0.34
     공간
    0.34
    POSITIVE LOGITS
     flows
    0.71
    流
    0.64
     flow
    0.63
     Flows
    0.62
     stream
    0.60
     flujo
    0.59
     aliran
    0.58
     Flow
    0.56
     flusso
    0.56
     جریان
    0.55
    Activations Density 0.065%

    No Known Activations