© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101011
    Prev
    Next
    INDEX
    Explanations

    scene descriptions

    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_14_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
    ッ
    0.38
    MDEwOlJlcG
    0.37
    פתח
    0.36
    入射
    0.36
    OR
    0.34
    ";
    0.33
     politik
    0.33
    »،
    0.33
    aaS
    0.33
     该
    0.33
    POSITIVE LOGITS
     гру
    0.39
     deterioro
    0.38
     cần
    0.37
     brauchen
    0.36
     behöver
    0.36
     tendre
    0.36
     besoin
    0.35
     deterioration
    0.35
     pequeña
    0.35
    alarını
    0.35
    Activations Density 0.061%

    No Known Activations