© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258638
    Prev
    Next
    INDEX
    Explanations

    link href=

    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_22_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
     الهمزه
    0.51
    𝙃
    0.49
     digitalisation
    0.48
     epidermis
    0.46
     olas
    0.44
    وینت
    0.44
     diploid
    0.42
     դ
    0.42
     digitalization
    0.42
    נדי
    0.41
    POSITIVE LOGITS
     There
    0.42
    くに
    0.40
     वक्त
    0.39
     Recharge
    0.39
    remember
    0.38
     Preserve
    0.38
     Championship
    0.38
     Safari
    0.38
    жер
    0.37
    escue
    0.37
    Activations Density 0.000%

    No Known Activations