© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32012
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     функции
    0.50
     функції
    0.45
     cent
    0.42
    뚱
    0.42
     function
    0.41
     Glor
    0.41
     тя
    0.40
     Funktion
    0.40
    姗
    0.40
    Glor
    0.39
    POSITIVE LOGITS
    state
    0.56
     state
    0.55
    STATE
    0.54
     STATE
    0.53
    State
    0.51
     State
    0.50
     სახელმწიფო
    0.48
     Staats
    0.46
     espaços
    0.46
     estatal
    0.45
    Activations Density 0.018%

    No Known Activations