© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163104
    Prev
    Next
    INDEX
    Explanations

    court names and specific German locations

    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_31_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
    dept
    0.38
    ທີ່ຈະ
    0.37
     Wisconsin
    0.37
     ador
    0.35
     కారణంగా
    0.34
    нува
    0.34
    푸
    0.34
     força
    0.33
    पना
    0.33
    viewModel
    0.33
    POSITIVE LOGITS
     screen
    0.40
    Secondly
    0.38
    Subtract
    0.37
    )+
    0.37
     subtracted
    0.36
    itteln
    0.36
    났다
    0.35
     screened
    0.35
     화면
    0.35
    ение
    0.35
    Activations Density 0.000%

    No Known Activations