© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183560
    Prev
    Next
    INDEX
    Explanations

    roman numerals and numbers with sections

    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_29_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
    FIFA
    0.34
    जयपुर
    0.33
    niv
    0.33
    閤
    0.33
    柩
    0.32
    alien
    0.32
     komb
    0.32
    arith
    0.31
     Package
    0.31
     solidarity
    0.31
    POSITIVE LOGITS
     ChatGPT
    0.34
     °,
    0.33
    嚼
    0.33
     கொரோ
    0.32
     Laurel
    0.31
    帖
    0.30
     появляется
    0.30
    毎回
    0.30
    飾
    0.30
     Defining
    0.30
    Activations Density 0.000%

    No Known Activations