© 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. 146718
    Prev
    Next
    INDEX
    Explanations

    have been 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_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
     하지
    0.52
    --,
    0.52
     brez
    0.51
     ആദ്യ
    0.51
    현재
    0.51
    쐞
    0.50
    GMP
    0.50
    ৩০
    0.49
    력이
    0.49
    zani
    0.49
    POSITIVE LOGITS
     بشأن
    0.47
    𝐦
    0.46
     {\
    0.45
    чами
    0.45
    м
    0.45
     राशियों
    0.44
     своих
    0.44
    мок
    0.44
    ăng
    0.44
    𝗺
    0.44
    Activations Density 0.000%

    No Known Activations