© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92861
    Prev
    Next
    INDEX
    Explanations

    to followed by verb

    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_11_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
     represent
    0.57
    ل
    0.54
    ov
    0.52
    to
    0.50
    idious
    0.50
     revolution
    0.49
     निर
    0.49
     idiot
    0.49
    y
    0.49
    ल
    0.48
    POSITIVE LOGITS
    cision
    0.67
     başarı
    0.63
    petite
    0.59
    бору
    0.59
    রম
    0.57
    .•
    0.57
    jarige
    0.57
    ‚¬
    0.57
    ;
    0.57
    am
    0.57
    Activations Density 0.003%

    No Known Activations