© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168178
    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
     एक्सपेक्ट
    0.38
    ="#!"
    0.38
     FormGroup
    0.38
    ꒪
    0.37
     PEC
    0.37
     mixtures
    0.37
     randomised
    0.36
    natures
    0.36
    ﺀ
    0.36
    PEC
    0.35
    POSITIVE LOGITS
     zam
    0.39
    Publisher
    0.39
     Wait
    0.36
     ura
    0.35
     Zam
    0.35
    ができる
    0.34
     Publisher
    0.34
     குறு
    0.34
     yea
    0.33
    setPointSize
    0.33
    Activations Density 0.000%

    No Known Activations