© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165458
    Prev
    Next
    INDEX
    Explanations

    multiple languages, often plural or quantifiers

    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_13_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
    ג
    0.45
    zeum
    0.43
    ט
    0.43
    ה
    0.42
    ందూ
    0.42
    Пре
    0.41
     ನಂತರ
    0.41
    ɦ
    0.41
    στημα
    0.40
    hado
    0.40
    POSITIVE LOGITS
     bean
    0.50
     medicina
    0.49
     an
    0.48
     da
    0.47
     fă
    0.47
    ed
    0.46
     été
    0.45
    oi
    0.44
     atti
    0.44
     one
    0.44
    Activations Density 0.006%

    No Known Activations