© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88571
    Prev
    Next
    INDEX
    Explanations

    I

    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_60_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
    costs
    0.48
    K
    0.47
    am
    0.46
    must
    0.44
    Costs
    0.43
    AM
    0.42
    KQ
    0.41
    S
    0.41
    C
    0.41
    Must
    0.40
    POSITIVE LOGITS
     people
    1.52
    people
    1.27
     mensen
    1.20
    People
    1.14
     людей
    1.14
     люди
    1.10
     लोगों
    1.06
     PEOPLE
    1.05
     People
    1.05
     should
    1.04
    Activations Density 0.002%

    No Known Activations