© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33057
    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_7_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
     of
    0.51
    (
    0.51
     de
    0.46
     be
    0.45
     Topological
    0.45
     ‘
    0.44
     ji
    0.44
     Targeted
    0.44
     agar
    0.43
     del
    0.43
    POSITIVE LOGITS
    pickMenu
    0.55
    榷
    0.53
    ClrBit
    0.52
    revalidator
    0.51
    ncnc
    0.51
    iteiten
    0.50
    windowActionBar
    0.50
     Elytres
    0.49
    preliquidacion
    0.49
    securityMarks
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.