© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2110
    Prev
    Next
    INDEX
    Explanations

    substitute into equation

    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
    AssemblyInfo
    0.37
    瘤
    0.37
    Numbers
    0.36
    numerical
    0.36
     черво
    0.36
     Clause
    0.36
    omena
    0.35
    Dul
    0.35
     числа
    0.35
    数为
    0.34
    POSITIVE LOGITS
     korral
    0.35
     rurales
    0.35
    vidas
    0.35
    icea
    0.35
    呐
    0.34
    ørt
    0.34
    갬
    0.34
    साइड
    0.33
    CID
    0.33
    辭
    0.33
    Activations Density 0.020%

    No Known Activations