© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7613
    Prev
    Next
    INDEX
    Explanations

    make a

    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_40_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
     Na
    0.39
    狼
    0.38
     Nationals
    0.37
     Antrieb
    0.37
    凝
    0.36
    Graphical
    0.36
     Waz
    0.36
     graphic
    0.36
     Gee
    0.36
    ះ
    0.36
    POSITIVE LOGITS
     fucking
    0.40
     stipulation
    0.37
    brand
    0.36
    bmc
    0.35
     пунктов
    0.35
    fuck
    0.34
    nego
    0.34
     thresholds
    0.34
    }^{-\
    0.34
    ющегося
    0.33
    Activations Density 0.022%

    No Known Activations