© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57446
    Prev
    Next
    INDEX
    Explanations

    convertible car features

    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
    colare
    0.54
    wärm
    0.54
    छत्तीस
    0.54
    urés
    0.53
    meyen
    0.51
     Absch
    0.51
    Après
    0.50
    廷
    0.50
    عات
    0.50
     jugo
    0.49
    POSITIVE LOGITS
     sej
    0.56
     veranda
    0.55
    ส
    0.55
     booth
    0.54
     Booth
    0.54
     Beach
    0.53
     rivulet
    0.53
     হইয়৷
    0.52
    з
    0.52
    iy
    0.51
    Activations Density 0.011%

    No Known Activations