© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54033
    Prev
    Next
    INDEX
    Explanations

    UK prime minister

    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_31_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
    pile
    0.37
     cmap
    0.36
     bursts
    0.35
    booked
    0.35
    thrift
    0.35
     ғ
    0.34
    Tau
    0.34
    承
    0.33
    tmp
    0.33
    ந்
    0.33
    POSITIVE LOGITS
     Taxes
    0.43
     Tax
    0.42
    hezza
    0.40
     налого
    0.39
     बालिका
    0.38
     Hardware
    0.38
    ইর
    0.38
     Taxation
    0.37
     Hall
    0.37
    Tax
    0.37
    Activations Density 0.002%

    No Known Activations