© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178496
    Prev
    Next
    INDEX
    Explanations

    python import keras

    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_24_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
    IRA
    0.46
    است
    0.42
    婍
    0.42
    нах
    0.39
    най
    0.38
    يره
    0.37
    }}=\
    0.37
    keszt
    0.37
    زد
    0.36
    Confirmed
    0.36
    POSITIVE LOGITS
     نیشنل
    0.45
     бясплатна
    0.43
     निर्म
    0.39
     Vivo
    0.38
     ಸರ್ಕಾರ
    0.38
    ileno
    0.38
    என்ன
    0.37
    imiento
    0.37
    ὢ
    0.37
     reconnect
    0.36
    Activations Density 0.001%

    No Known Activations