© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64363
    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_46_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
    楽し
    0.38
     sheaves
    0.38
    鑑
    0.35
    ದಯ
    0.35
     touching
    0.35
    illus
    0.35
     workbench
    0.35
    鑒
    0.35
    を楽し
    0.35
    ದ್ದರಿಂದ
    0.35
    POSITIVE LOGITS
     Conservative
    0.43
    })_{\
    0.40
     Naira
    0.40
     gratuito
    0.39
     Raw
    0.38
     Wel
    0.38
    hém
    0.38
     bé
    0.37
     gratuite
    0.37
     Slip
    0.37
    Activations Density 0.000%

    No Known Activations