© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64294
    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_46_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
     táct
    0.42
     Kubo
    0.41
    雙
    0.41
    Att
    0.40
    یاط
    0.39
    ွယ်
    0.39
     پشتی
    0.39
    ราย
    0.38
    Drink
    0.36
    술
    0.36
    POSITIVE LOGITS
     AR
    0.43
     аре
    0.40
     Stream
    0.39
    Gl
    0.36
     Suède
    0.36
    gl
    0.36
    STREAM
    0.36
    bodied
    0.36
     vérité
    0.36
    GALAD
    0.35
    Activations Density 0.000%

    No Known Activations