© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77329
    Prev
    Next
    INDEX
    Explanations

    sentence completion

    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_31_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
     lesions
    0.36
    arsenic
    0.36
    lás
    0.36
    ँव
    0.35
    牆
    0.35
     ~(~)
    0.35
    陽
    0.35
    场景
    0.35
    icznych
    0.35
     semelh
    0.34
    POSITIVE LOGITS
     Pro
    0.44
     imperative
    0.42
    Accordingly
    0.38
     CASCADE
    0.37
    考虑到
    0.37
     Determined
    0.37
    滘
    0.37
    गोवा
    0.37
     Unlike
    0.36
    Укупно
    0.36
    Activations Density 0.014%

    No Known Activations