© 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. 241620
    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
     упро
    0.49
     simplifying
    0.48
     simplification
    0.46
    凪
    0.45
     Simplify
    0.44
     simplify
    0.44
     sempl
    0.44
     क्‍या
    0.43
     इंपोर्टेंट
    0.43
    Simplify
    0.42
    POSITIVE LOGITS
     give
    0.41
    给
    0.40
    給你
    0.40
     donnant
    0.38
    give
    0.38
    出去
    0.37
     giving
    0.37
    alker
    0.37
     Giving
    0.36
    ATER
    0.36
    Activations Density 0.009%

    No Known Activations