© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17589
    Prev
    Next
    INDEX
    Explanations

    excuse generating

    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_15_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
    метри
    0.25
    ↵
    0.24
     Friction
    0.24
    ’?
    0.24
     knows
    0.23
     வெற்ற
    0.23
    ïs
    0.23
     sveta
    0.23
     Doors
    0.23
    uv
    0.22
    POSITIVE LOGITS
    ωσε
    0.25
    VSLU
    0.24
    胄
    0.22
    乃
    0.22
    当中
    0.22
    ccos
    0.22
    pped
    0.21
     substantive
    0.21
    ahal
    0.21
    敀
    0.21
    Activations Density 0.127%

    No Known Activations