© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169801
    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_56_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
    Treasurer
    0.24
    Historically
    0.22
    BigDecimal
    0.22
    /');
    0.22
    Stud
    0.22
    reveal
    0.21
    Additionally
    0.21
    SPEED
    0.21
    Dy
    0.21
    ༤
    0.21
    POSITIVE LOGITS
     த
    0.24
     distra
    0.24
     Nombre
    0.24
     Part
    0.23
     에
    0.23
     langs
    0.23
     Teil
    0.23
     ESP
    0.23
     JAPAN
    0.22
     ‘
    0.22
    Activations Density 0.000%

    No Known Activations