© 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. 193901
    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
     aproxim
    0.45
     pptn
    0.42
     Cnemidophorus
    0.41
     Puede
    0.40
     AcOEt
    0.40
     prebiotic
    0.40
    艱
    0.39
     ціка
    0.39
     Actualmente
    0.39
     cyclin
    0.39
    POSITIVE LOGITS
    uski
    0.40
    et
    0.39
    apa
    0.39
    ri
    0.38
    hape
    0.38
    p
    0.37
    ampak
    0.36
    ymet
    0.35
    ete
    0.35
    si
    0.35
    Activations Density 0.000%

    No Known Activations