© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27017
    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_40_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
    programming
    0.40
    इंट
    0.39
     Nin
    0.38
     nin
    0.38
    guards
    0.37
    瞞
    0.36
     ১১
    0.35
     Nine
    0.35
     ch
    0.35
     nine
    0.35
    POSITIVE LOGITS
    PerTrial
    0.41
     ৬০
    0.39
     surpl
    0.39
    六年
    0.38
    㕣
    0.38
    BeerItem
    0.37
     Upl
    0.36
     наук
    0.36
     vision
    0.35
    Ivo
    0.35
    Activations Density 0.004%

    No Known Activations