© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36265
    Prev
    Next
    INDEX
    Explanations

    testosterone or test tube

    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_3_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
    ק
    0.71
    פ
    0.71
    一
    0.70
    fordern
    0.67
    很
    0.66
     inductor
    0.66
    ي
    0.66
     пациен
    0.64
    iconfont
    0.64
     étape
    0.64
    POSITIVE LOGITS
    ud
    0.65
    US
    0.63
    amm
    0.60
    sa
    0.60
     uptick
    0.60
    ro
    0.59
    amer
    0.59
    ş
    0.58
    åg
    0.58
     मीडियावर
    0.57
    Activations Density 0.018%

    No Known Activations