© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54553
    Prev
    Next
    INDEX
    Explanations

    people

    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_55_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
    ebut
    0.38
     ASGI
    0.36
    webp
    0.36
    нави
    0.36
     zw
    0.35
     Gob
    0.35
    ────────
    0.35
     Сі
    0.35
    Hepin
    0.34
    轪
    0.34
    POSITIVE LOGITS
     gente
    1.93
    gente
    1.49
     Gente
    1.44
     people
    1.27
    people
    1.24
    People
    1.20
     People
    1.15
     PEOPLE
    1.06
     ljudi
    1.05
     mensen
    1.03
    Activations Density 0.000%

    No Known Activations