© 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. 48567
    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
     корреспонд
    0.41
    ம்பர
    0.37
     интерес
    0.36
    मर्रा
    0.36
    糉
    0.36
    CameraOpened
    0.36
     సంవ
    0.35
     завод
    0.35
    জ্জনক
    0.35
    枇
    0.35
    POSITIVE LOGITS
    ître
    0.42
     either
    0.39
    lichkeiten
    0.37
    劇場
    0.35
     Gravity
    0.35
     historically
    0.33
    🚫
    0.32
     तया
    0.32
    PlatformTarget
    0.32
    ِر
    0.31
    Activations Density 0.000%

    No Known Activations