© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133325
    Prev
    Next
    INDEX
    Explanations

    Pakistani politicians

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    residual
    0.44
     residual
    0.41
    jeta
    0.41
     PLC
    0.40
    銖
    0.39
     Residual
    0.39
    Residual
    0.39
    чал
    0.39
    ೬
    0.38
    Beg
    0.38
    POSITIVE LOGITS
     Sash
    0.40
    SUS
    0.40
     sut
    0.38
    ipated
    0.38
    NAM
    0.38
     नार
    0.37
    Nazi
    0.37
     naz
    0.37
    athlon
    0.37
     swivel
    0.36
    Activations Density 0.000%

    No Known Activations