© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127471
    Prev
    Next
    INDEX
    Explanations

    name, descendant, shadow, Lord, father, beast, face

    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_37_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
     ialah
    0.45
     sinners
    0.43
     humankind
    0.42
    patri
    0.42
    助
    0.42
     asimismo
    0.41
    篇
    0.41
     神
    0.41
     producido
    0.41
     sacraments
    0.41
    POSITIVE LOGITS
    ामान्य
    0.38
     Whilst
    0.37
    ပုံ
    0.36
     যেকোন
    0.36
    турой
    0.36
     ভাঙ্গ
    0.35
     Einf
    0.35
     Enfin
    0.35
     sowas
    0.34
     facteur
    0.34
    Activations Density 0.000%

    No Known Activations