© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174247
    Prev
    Next
    INDEX
    Explanations

    protein deacylase or ATPase

    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_20_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
     crescent
    0.13
    zeta
    0.12
    ثیر
    0.12
    矩
    0.12
    三种
    0.12
     calibre
    0.12
    _{
    0.12
    ഛ
    0.12
     Qt
    0.12
    ┤
    0.12
    POSITIVE LOGITS
     schaffen
    0.16
    Loksatta
    0.16
     🥰
    0.15
    aper
    0.14
    IEC
    0.14
     ক্ষয়
    0.14
    IPOP
    0.14
    changes
    0.14
     falls
    0.14
     changements
    0.14
    Activations Density 0.006%

    No Known Activations