© 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. 37746
    Prev
    Next
    INDEX
    Explanations

    consistent / agree / consent

    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
    7
    0.58
    AZ
    0.57
    _{
    0.56
    ב
    0.56
    _{\
    0.54
    Track
    0.54
    ب
    0.54
    ब
    0.54
    ES
    0.53
    ات
    0.53
    POSITIVE LOGITS
    ancienne
    0.55
    oxi
    0.55
    osition
    0.53
     सितंबर
    0.53
    ෙහි
    0.52
     його
    0.51
     ໃນ
    0.51
     viejo
    0.51
     ਹੈ
    0.50
    posición
    0.50
    Activations Density 0.001%

    No Known Activations