© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 102179
    Prev
    Next
    INDEX
    Explanations

    looking

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     candle
    0.78
     candlelight
    0.77
     Candle
    0.75
    candle
    0.73
     lantern
    0.70
     candles
    0.65
    燭
    0.64
    烛
    0.61
     lanterns
    0.59
     torch
    0.58
    POSITIVE LOGITS
    PIN
    0.40
    NIC
    0.37
    哥
    0.36
     signific
    0.36
    MSA
    0.36
    exact
    0.35
    PSA
    0.35
    ydat
    0.35
    assa
    0.35
     NIC
    0.35
    Activations Density 0.003%

    No Known Activations