© 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. 242108
    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
    次元
    0.38
     Silber
    0.38
    スープ
    0.37
     Arroyo
    0.37
     Dickinson
    0.37
    "]]
    0.37
     Arac
    0.36
    Donate
    0.36
     Brett
    0.36
     {_
    0.36
    POSITIVE LOGITS
    simplified
    0.43
     smoothed
    0.42
     तुम्हारी
    0.42
     totalled
    0.39
     embedded
    0.39
    published
    0.39
    groomed
    0.39
     published
    0.38
    लिये
    0.38
     Simplified
    0.38
    Activations Density 0.000%

    No Known Activations