© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204616
    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_56_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
    preserving
    0.41
    )—
    0.39
    コ
    0.38
    ingale
    0.38
    —
    0.38
     archiving
    0.37
     realize
    0.36
    growing
    0.36
    calibrate
    0.36
    giving
    0.36
    POSITIVE LOGITS
     Cord
    0.41
     Vikt
    0.39
     Ip
    0.39
    囃
    0.38
     Holt
    0.38
     osztály
    0.37
     Shabbat
    0.37
    澀
    0.37
     Canadi
    0.37
    Cordial
    0.37
    Activations Density 0.000%

    No Known Activations