© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45515
    Prev
    Next
    INDEX
    Explanations

    stages of

    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_3_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
    i
    0.70
    really
    0.58
    IM
    0.54
    يها
    0.54
    t
    0.54
     сдела
    0.54
    Really
    0.54
     рассказа
    0.53
    ihe
    0.52
     нашли
    0.52
    POSITIVE LOGITS
    ด
    0.72
    مه
    0.69
     init
    0.68
    ه
    0.66
    К
    0.66
    ्य
    0.64
     menurut
    0.62
     jau
    0.61
     ini
    0.61
     inic
    0.60
    Activations Density 0.001%

    No Known Activations