© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150390
    Prev
    Next
    INDEX
    Explanations

    btn

    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_18_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
    3
    0.59
    4
    0.56
    ai
    0.55
    ol
    0.53
    ub
    0.52
    left
    0.51
    0
    0.49
    ung
    0.48
     Preferably
    0.48
    k
    0.47
    POSITIVE LOGITS
    енера
    0.51
     licensure
    0.51
     resposta
    0.50
     resumes
    0.50
    спу
    0.50
     encephal
    0.50
     популя
    0.50
    ेंसी
    0.49
     nghiên
    0.49
     scheda
    0.48
    Activations Density 0.000%

    No Known Activations