© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134152
    Prev
    Next
    INDEX
    Explanations

    C-suite executives

    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_6_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
    in
    1.34
    as
    1.20
    ia
    1.16
    o
    1.09
    ur
    1.06
    ave
    1.05
    an
    1.05
    ના
    1.05
    ert
    1.03
    ný
    1.02
    POSITIVE LOGITS
     divulg
    1.29
     trein
    0.92
     transporter
    0.84
     calibr
    0.83
     nutritive
    0.83
     antider
    0.82
     vien
    0.81
     configur
    0.81
     multiplic
    0.81
    ट
    0.80
    Activations Density 0.000%

    No Known Activations