© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120077
    Prev
    Next
    INDEX
    Explanations

    digits followed by operators

    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_27_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
     農
    0.38
    蛋白質
    0.37
    额外
    0.37
    Protein
    0.36
    ους
    0.36
    誅
    0.36
     HEN
    0.36
    సాయ
    0.35
     HUGH
    0.34
    ぞれ
    0.34
    POSITIVE LOGITS
     typical
    0.45
     It
    0.43
     it
    0.42
     Talia
    0.42
     점
    0.41
    atisf
    0.41
     Points
    0.40
     दशा
    0.39
     Typical
    0.39
     e
    0.38
    Activations Density 0.002%

    No Known Activations