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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196019
    Prev
    Next
    INDEX
    Explanations

    special keywords after specific tokens

    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_26_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
     odors
    0.38
    lineNumber
    0.38
     drizzle
    0.38
    δ
    0.37
     tink
    0.37
    iemi
    0.37
     constellation
    0.36
     luminal
    0.36
    ₅
    0.36
    ump
    0.36
    POSITIVE LOGITS
     ziek
    0.45
     Twice
    0.38
     desempeñ
    0.38
     výkon
    0.37
     সাপ্তাহ
    0.36
     बीमार
    0.35
     Thirdly
    0.35
    헹
    0.34
     vlastní
    0.34
    鐟
    0.34
    Activations Density 0.000%

    No Known Activations