© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199263
    Prev
    Next
    INDEX
    Explanations

    regions, nationalities, sports leagues

    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_12_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
    atoti
    0.64
    ืช
    0.59
     =-\
    0.54
    akarane
    0.51
    䀼
    0.51
     الاستفهام
    0.50
     букмекерлер
    0.50
     አበባ
    0.50
    드의
    0.50
     calyce
    0.50
    POSITIVE LOGITS
    A
    0.64
     &
    0.64
     Sob
    0.61
     V
    0.58
    ja
    0.56
     A
    0.55
     by
    0.55
     than
    0.55
     ~
    0.55
     Sur
    0.55
    Activations Density 0.000%

    No Known Activations