© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52111
    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_55_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
    forbidden
    0.38
    badlogic
    0.38
    uchos
    0.38
    ActionEvent
    0.38
    mnopqr
    0.38
     impulse
    0.37
     eliminación
    0.37
    ϭ
    0.37
    Radial
    0.37
    Unable
    0.36
    POSITIVE LOGITS
    他們
    0.58
     cav
    0.52
     Will
    0.52
     Cav
    0.52
     cavitation
    0.50
     they
    0.49
     Come
    0.49
     WILL
    0.49
     Kav
    0.49
     THEY
    0.49
    Activations Density 0.000%

    No Known Activations