© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153660
    Prev
    Next
    INDEX
    Explanations

    data-testid attributes

    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
     arsine
    0.38
     illuminating
    0.38
    鍬
    0.38
    वेश
    0.37
    |"
    0.37
    కోవ
    0.36
     lā
    0.36
     বিকা
    0.36
     laboratories
    0.35
     wyt
    0.35
    POSITIVE LOGITS
     worthless
    0.40
     placeholder
    0.38
     meaningless
    0.38
     oldCount
    0.37
     useless
    0.36
    ')}
    0.36
     boolean
    0.36
     उदासीन
    0.36
    efeu
    0.35
    IED
    0.35
    Activations Density 0.000%

    No Known Activations