© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139337
    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_37_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
     showings
    0.40
     controlador
    0.38
     Osw
    0.36
    azaki
    0.36
     ταιν
    0.34
     twe
    0.33
     rağmen
    0.33
     带
    0.33
     Tapatalk
    0.33
    ENDED
    0.32
    POSITIVE LOGITS
    نك
    0.42
    peu
    0.39
    فوظ
    0.37
    孤
    0.37
    ciences
    0.35
    Brewer
    0.35
    IsNullOrEmpty
    0.35
     deficiency
    0.34
    पि
    0.34
    ากาศ
    0.34
    Activations Density 0.000%

    No Known Activations