© 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. 32074
    Prev
    Next
    INDEX
    Explanations

    Haiti, San Juan

    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
     Haiti
    0.40
    mul
    0.39
    ).__
    0.38
     নাইট
    0.38
     mul
    0.37
    amal
    0.37
    )").
    0.36
     Haitian
    0.36
     Avner
    0.36
     taxable
    0.35
    POSITIVE LOGITS
    ậ
    0.42
    িল্লা
    0.41
    乐
    0.40
    榴
    0.40
    Doll
    0.39
     ALLOYS
    0.38
    蘸
    0.38
    Donor
    0.38
     plasma
    0.38
     belanja
    0.38
    Activations Density 0.004%

    No Known Activations