© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124335
    Prev
    Next
    INDEX
    Explanations

    <0xF0><0x9F><0xA6><0xA5> emoji

    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_3_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
    d
    1.31
    st
    1.00
    a
    0.99
    f
    0.97
    د
    0.87
    ד
    0.83
    lük
    0.82
    𝟬
    0.82
    ।
    0.78
    s
    0.77
    POSITIVE LOGITS
    та
    1.00
     n
    0.85
    т
    0.84
    সহ
    0.84
    u
    0.82
    و
    0.80
    ض
    0.80
    مي
    0.79
    ва
    0.79
    og
    0.78
    Activations Density 0.000%

    No Known Activations