© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40128
    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_57_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
     przew
    0.48
     Bu
    0.48
    Bu
    0.42
    乐
    0.41
     bu
    0.40
     harta
    0.40
    樂
    0.39
    危害
    0.38
     Mica
    0.38
    楽
    0.38
    POSITIVE LOGITS
     cure
    0.40
    হয়
    0.38
    ából
    0.38
    ㄚ
    0.37
     fellowship
    0.36
     cook
    0.35
     provisional
    0.35
    usages
    0.35
    rát
    0.34
     cures
    0.34
    Activations Density 0.000%

    No Known Activations