© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205724
    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_10_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
     overfitting
    0.55
     cohom
    0.53
     analogs
    0.52
     accolades
    0.51
    𝙜
    0.51
     analogies
    0.49
     analyt
    0.49
     essays
    0.46
     सिंगिंग
    0.46
    na
    0.45
    POSITIVE LOGITS
    AR
    0.54
    น
    0.47
    ară
    0.46
    с
    0.46
    は
    0.46
     zakres
    0.46
    ът
    0.44
    너
    0.44
    작
    0.44
    ایه
    0.43
    Activations Density 0.000%

    No Known Activations