© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18426
    Prev
    Next
    INDEX
    Explanations

    family members

    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_40_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
    ┈
    0.39
     गुण
    0.37
    ੯
    0.35
    дки
    0.35
     높아
    0.35
     liegen
    0.34
     sữa
    0.33
     patties
    0.33
     assemblages
    0.33
    댈
    0.32
    POSITIVE LOGITS
     members
    2.50
    Members
    2.22
    members
    2.19
    成员
    2.19
     miembros
    2.13
    メンバー
    2.09
     membros
    2.09
     membres
    2.03
     Members
    2.02
    成員
    2.02
    Activations Density 0.087%

    No Known Activations