© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43160
    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_22_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
    𝘇
    0.43
    UTIONS
    0.43
    constraints
    0.42
    missible
    0.41
    ॉर्डिंग
    0.40
     optically
    0.40
    更有
    0.40
    ದ್ದರಿಂದ
    0.40
    TextureAsset
    0.40
    ंग
    0.39
    POSITIVE LOGITS
     Muc
    0.45
    inan
    0.40
    enea
    0.40
     CPC
    0.39
    標
    0.39
    الم
    0.39
     vitesse
    0.39
     تعرف
    0.39
     ?:
    0.39
    COc
    0.38
    Activations Density 0.000%

    No Known Activations