© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195489
    Prev
    Next
    INDEX
    Explanations

    concrete mix design

    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_15_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
    vpn
    0.54
    b
    0.53
     rows
    0.50
    Produkt
    0.50
    produkt
    0.49
    productions
    0.49
    queleto
    0.49
     trench
    0.47
     mussten
    0.47
    Comments
    0.47
    POSITIVE LOGITS
     Constituency
    0.54
     HTMLSc
    0.53
     liya
    0.52
    ୭
    0.50
    ymo
    0.50
    变得
    0.50
     pariy
    0.49
     detainees
    0.49
    мимо
    0.48
     ಇನ್ನ
    0.48
    Activations Density 0.002%

    No Known Activations