© 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. 208897
    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
    aber
    0.48
     Vereins
    0.46
     Geschäft
    0.46
     Language
    0.45
     heroic
    0.44
    䜣
    0.44
    zus
    0.43
     But
    0.42
    o
    0.42
     Букмекердик
    0.41
    POSITIVE LOGITS
    غذ
    0.55
    ラックス
    0.51
    쐞
    0.51
     bioge
    0.50
    microwave
    0.49
     alimentaires
    0.49
    ご
    0.48
     фармацев
    0.48
     chimiques
    0.48
     mangroves
    0.48
    Activations Density 0.000%

    No Known Activations