© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97492
    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_14_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
    r
    0.60
    dg
    0.54
    d
    0.51
    nd
    0.50
     regard
    0.47
    v
    0.46
     DST
    0.44
    du
    0.43
     BILL
    0.43
    READER
    0.42
    POSITIVE LOGITS
    کین
    0.52
    ómicas
    0.50
    膿
    0.48
     genus
    0.47
     بیاکتنې
    0.47
     pawn
    0.47
    wania
    0.47
    انی
    0.46
     sizin
    0.46
     femenino
    0.46
    Activations Density 0.000%

    No Known Activations