© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208259
    Prev
    Next
    INDEX
    Explanations

    acting up or out

    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_10_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
    ح
    0.81
     във
    0.74
     toyota
    0.70
     chromedp
    0.68
     emocional
    0.65
     internacional
    0.65
     ${({
    0.64
     daimyo
    0.63
    شل
    0.63
     idioma
    0.63
    POSITIVE LOGITS
     are
    0.57
    Insert
    0.57
     மாற்ற
    0.54
    Inset
    0.52
    失敗
    0.52
     a
    0.52
    ру
    0.52
    Bew
    0.51
    post
    0.50
    Residual
    0.50
    Activations Density 0.001%

    No Known Activations