© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86625
    Prev
    Next
    INDEX
    Explanations

    storage bins shelves boxes dividers

    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_23_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
    剪
    0.35
    পাড়
    0.35
    <code>
    0.35
    COO
    0.34
     phẩm
    0.34
    矮
    0.34
    品
    0.33
    ANN
    0.32
    匹
    0.32
    PWD
    0.32
    POSITIVE LOGITS
     delicious
    0.39
     createTask
    0.39
     diseases
    0.37
     energie
    0.37
     crear
    0.36
    টিয়
    0.36
     initializing
    0.36
     courbes
    0.36
     enticing
    0.35
    createText
    0.35
    Activations Density 0.001%

    No Known Activations