© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17423
    Prev
    Next
    INDEX
    Explanations

    amounts or specific values

    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
     बेर
    0.36
     몰
    0.36
     আ
    0.36
     میر
    0.35
    ৫০
    0.35
    đồng
    0.35
    鉞
    0.35
     joe
    0.35
     शो
    0.34
     lever
    0.34
    POSITIVE LOGITS
     dès
    0.42
     шести
    0.41
    ุก
    0.39
    ໑
    0.39
    ╣
    0.39
     العافيه
    0.39
    &#
    0.38
    FormField
    0.37
     Sixth
    0.37
    
    0.36
    Activations Density 0.014%

    No Known Activations