© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242283
    Prev
    Next
    INDEX
    Explanations

    nationalities and professions

    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
     estadounid
    0.40
     наме
    0.40
     consequências
    0.38
     رکھ
    0.37
    derick
    0.37
    汙
    0.36
    ماغ
    0.36
    ➠
    0.35
    leftrightarrow
    0.34
     consequences
    0.34
    POSITIVE LOGITS
    thirsty
    0.43
     guru
    0.42
    ுறு
    0.42
    ous
    0.42
     Lesbian
    0.40
     Conservative
    0.39
    guru
    0.39
     चौ
    0.39
    Conservative
    0.38
    TEC
    0.38
    Activations Density 0.003%

    No Known Activations