© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242664
    Prev
    Next
    INDEX
    Explanations

    Oracle database systems

    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_40_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
     IDE
    0.42
    ///////////////
    0.37
    ذك
    0.36
    rauch
    0.35
    ?????
    0.35
    ክት
    0.35
     histor
    0.35
     সার
    0.34
    潮
    0.34
    ????????
    0.34
    POSITIVE LOGITS
    etan
    0.41
    Bridge
    0.40
    essages
    0.38
     Hait
    0.38
    wikk
    0.38
     patham
    0.37
    Penn
    0.36
    elina
    0.35
    ophora
    0.34
    Executor
    0.34
    Activations Density 0.003%

    No Known Activations