© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17815
    Prev
    Next
    INDEX
    Explanations

    historical latin texts

    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_34_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
     fördern
    0.42
    wertung
    0.39
     kalite
    0.38
     fonksiyon
    0.38
    wicket
    0.37
     каче
    0.37
    ahydro
    0.37
    浻
    0.37
     వు
    0.36
    甙
    0.36
    POSITIVE LOGITS
    可以说
    0.38
     एशिया
    0.38
    Pont
    0.36
     primate
    0.36
    rue
    0.35
    pe
    0.35
     Equ
    0.35
    تاج
    0.35
     Pont
    0.35
     dispositivos
    0.35
    Activations Density 0.001%

    No Known Activations