© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 153958
    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_23_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
     árvore
    0.52
    ueuse
    0.45
    ঞ্চলের
    0.43
     sebebi
    0.43
     ausgezeichnet
    0.43
    Ş
    0.42
    पित
    0.41
     Bezeichnung
    0.41
    щают
    0.41
     adaptée
    0.41
    POSITIVE LOGITS
     Mont
    0.41
     ;
    0.39
     I
    0.38
     novel
    0.38
     Mari
    0.38
     //
    0.35
     Ven
    0.35
     rentals
    0.35
    other
    0.35
     Driver
    0.35
    Activations Density 0.000%

    No Known Activations