© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260712
    Prev
    Next
    INDEX
    Explanations

    enthusiasm

    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_5_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
    able
    1.34
    s
    1.33
    ically
    1.29
    ada
    1.24
    ators
    1.24
    ation
    1.10
    ant
    1.09
    ri
    1.08
    ations
    1.08
    ting
    1.08
    POSITIVE LOGITS
    مي
    1.62
    你
    1.38
    ==
    1.38
    هي
    1.37
    জন
    1.20
    ميل
    1.20
    <0xF3>
    1.17
    وك
    1.15
    ميم
    1.15
    نك
    1.15
    Activations Density 0.000%

    No Known Activations