© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 165612
    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_34_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
     gegen
    0.40
    ajna
    0.40
     yaklaş
    0.38
    ആര്‍
    0.37
    唂
    0.37
     স্বীকৃত
    0.37
    akap
    0.36
    ಆ
    0.36
     hängt
    0.36
     आगामी
    0.36
    POSITIVE LOGITS
     Seal
    0.39
     seal
    0.38
    seal
    0.36
     pianta
    0.36
    Seal
    0.36
     VOC
    0.35
     FXMLLoader
    0.35
     Aff
    0.35
     फ्लो
    0.34
     SEAL
    0.33
    Activations Density 0.000%

    No Known Activations