© 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
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60841
    Prev
    Next
    INDEX
    Explanations

    gaming laptop

    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_11_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
     doubting
    0.50
     harming
    0.47
     Kxb
    0.46
     doubted
    0.46
     hadron
    0.43
     reconstructing
    0.43
     mâle
    0.41
    𝖾
    0.41
     dared
    0.41
     Mancini
    0.41
    POSITIVE LOGITS
    ם
    0.42
    ों
    0.42
    أ
    0.39
     सड़कें
    0.38
    స్
    0.38
    ״
    0.38
    ओं
    0.38
     شاہ
    0.38
    Dengan
    0.38
    navigate
    0.37
    Activations Density 0.006%

    No Known Activations