© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1277
    Prev
    Next
    INDEX
    Explanations

    tense, grammar, voice, tenses

    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
     Tx
    0.42
     lbl
    0.39
     المدرسة
    0.38
     tx
    0.37
    眞
    0.37
     acceso
    0.36
    키
    0.35
     txn
    0.35
    ዻ
    0.34
    access
    0.34
    POSITIVE LOGITS
    📜
    0.38
    fik
    0.37
     necesitar
    0.37
    рики
    0.37
     Inspectors
    0.37
    Inspector
    0.37
    Dale
    0.37
     Inspector
    0.36
    LEASE
    0.36
    Camb
    0.36
    Activations Density 0.060%

    No Known Activations