© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111685
    Prev
    Next
    INDEX
    Explanations

    92% or 92 followed by units

    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_2_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
    /
    1.38
    1.27
    ,
    1.16
     de
    1.14
    ্ন
    1.07
    ز
    1.06
    St
    1.02
    -
    1.02
    Than
    1.00
    X
    0.96
    POSITIVE LOGITS
    는
    1.54
    ።
    1.41
    in
    1.38
    ра
    1.25
    ۔
    1.23
    다
    1.20
    ো
    1.20
    ления
    1.18
    ா
    1.18
    し
    1.16
    Activations Density 0.010%

    No Known Activations