© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86401
    Prev
    Next
    INDEX
    Explanations

    exit loop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     undo
    0.41
     braid
    0.40
     unity
    0.40
     reconstructions
    0.40
    敉
    0.39
     Trunk
    0.39
     Wound
    0.39
     Phal
    0.39
    ەل
    0.38
    estine
    0.37
    POSITIVE LOGITS
    зу
    0.38
    zub
    0.38
    اونلو
    0.36
    rime
    0.36
    Zur
    0.35
    ￢
    0.35
     Resources
    0.34
    Amenities
    0.34
    Resources
    0.33
    寜
    0.33
    Activations Density 0.001%

    No Known Activations