© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66294
    Prev
    Next
    INDEX
    Explanations

    FCA, SEC, FSA, SFC, investor, funds

    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_41_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
     rejest
    0.37
     regist
    0.36
     printr
    0.36
    ديث
    0.35
    orio
    0.35
    QE
    0.34
    支
    0.34
    ंपल
    0.34
    quinas
    0.34
    ˙
    0.34
    POSITIVE LOGITS
     Sip
    0.48
     sip
    0.47
     SFC
    0.42
     SIP
    0.42
     grilled
    0.39
     financière
    0.38
     Investor
    0.37
    бар
    0.36
     sift
    0.36
     recinto
    0.36
    Activations Density 0.024%

    No Known Activations