© 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. 182561
    Prev
    Next
    INDEX
    Explanations

    numbers, words, or punctuation

    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
    =[]
    0.40
     computador
    0.39
     cozinha
    0.39
     Putin
    0.38
     Koch
    0.38
     []
    0.37
     计算
    0.37
     Tổ
    0.37
     फुटबल
    0.37
     Tuy
    0.37
    POSITIVE LOGITS
    andidate
    0.41
     springs
    0.38
    ண்டு
    0.37
    candidate
    0.37
     چل
    0.36
    ья
    0.36
     వల్ల
    0.35
    ান্ট
    0.35
    thumbnails
    0.34
    ្រ
    0.34
    Activations Density 0.000%

    No Known Activations