© 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. 153263
    Prev
    Next
    INDEX
    Explanations

    `super.key` or `Key? key`

    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
     rather
    0.39
    𝜇
    0.38
     Rather
    0.37
    urized
    0.37
    constru
    0.36
    좔
    0.36
    ๙
    0.36
     yells
    0.36
     Приступ
    0.35
    rather
    0.35
    POSITIVE LOGITS
     BSc
    0.41
     Cisco
    0.41
    仅
    0.40
    芎
    0.40
    特
    0.39
     Anthrop
    0.38
     BERN
    0.38
    isco
    0.38
    翱
    0.37
    自定义
    0.37
    Activations Density 0.000%

    No Known Activations