© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58427
    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_59_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
     perin
    0.38
    ToAction
    0.38
    Webhook
    0.37
    ેશ
    0.35
    Bul
    0.34
     Peres
    0.34
    LLOW
    0.34
    罘
    0.34
     co
    0.33
    WriteLine
    0.33
    POSITIVE LOGITS
     po
    0.79
     Po
    0.67
    po
    0.65
    Po
    0.65
    ipo
    0.45
    ropo
    0.42
    ütz
    0.40
     poaching
    0.39
     Poincaré
    0.38
    pof
    0.38
    Activations Density 0.000%

    No Known Activations