© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133641
    Prev
    Next
    INDEX
    Explanations

    noun suffixes

    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_1_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
     poziom
    1.34
    選
    1.28
    選択
    1.26
    開始
    1.21
    出発
    1.18
    食べ
    1.16
    つけて
    1.16
    elijke
    1.15
     товар
    1.15
     cambiamento
    1.13
    POSITIVE LOGITS
    ,
    1.91
    .
    1.70
    ↵↵
    1.45
    ad
    1.42
    la
    1.38
    ra
    1.34
    ;
    1.30
    da
    1.27
    w
    1.26
    ar
    1.25
    Activations Density 0.001%

    No Known Activations