© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120763
    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_27_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
    ә
    0.29
    ье
    0.28
     permitted
    0.28
    糖尿病
    0.27
    ৱ
    0.27
     ка
    0.27
    юсь
    0.26
    ロッパ
    0.26
    ቾ
    0.26
    ដ្ឋ
    0.25
    POSITIVE LOGITS
     tratamientos
    0.29
     evidentemente
    0.27
     baut
    0.26
     corrige
    0.26
    (/
    0.25
     cinemat
    0.25
     beber
    0.25
     birbir
    0.25
     carattere
    0.25
     invertir
    0.25
    Activations Density 0.000%

    No Known Activations