© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24505
    Prev
    Next
    INDEX
    Explanations

    till, ut,að

    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
     to
    1.05
     (
    1.05
    ل
    1.05
    ル
    0.96
     they
    0.92
     this
    0.90
    Қ
    0.87
    to
    0.84
    ریس
    0.84
    at
    0.83
    POSITIVE LOGITS
    ين
    1.07
    t
    0.96
     capacitación
    0.87
     olvidado
    0.84
     riego
    0.82
     casado
    0.82
     darüber
    0.79
    ة
    0.79
     Führung
    0.77
    دين
    0.76
    Activations Density 0.000%

    No Known Activations