© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10973
    Prev
    Next
    INDEX
    Explanations

    Adam and Eve fall

    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_13_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
    :"
    0.51
    Alt
    0.50
    साम
    0.47
     ż
    0.44
    alei
    0.44
    D
    0.44
    agée
    0.44
     diminu
    0.44
    Descripción
    0.44
    ৭
    0.43
    POSITIVE LOGITS
     Kxa
    0.46
     Кан
    0.45
     Lichtenfels
    0.44
     conductas
    0.44
     conducta
    0.44
     Tree
    0.43
     خص
    0.43
     දෙ
    0.42
     Withers
    0.42
     Witten
    0.42
    Activations Density 0.020%

    No Known Activations