© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36401
    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_31_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
     Towns
    0.26
    づ
    0.26
     towns
    0.24
     bath
    0.24
    ଣ୍
    0.24
     when
    0.24
    ុន
    0.23
    Cha
    0.23
    Town
    0.23
     lu
    0.23
    POSITIVE LOGITS
    缄
    0.31
     ஆராய்ச்சி
    0.27
    砒
    0.27
     fortiter
    0.26
     bakalım
    0.26
     රස
    0.25
    生活的
    0.24
     поможет
    0.24
     falleció
    0.24
    ങ്ക്
    0.24
    Activations Density 0.010%

    No Known Activations