© 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. 155254
    Prev
    Next
    INDEX
    Explanations

    immigrant

    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
    y
    0.72
    ي
    0.55
    י
    0.47
     Дон
    0.45
    yue
    0.44
     Се
    0.42
    wee
    0.42
    ште
    0.40
    i
    0.40
    yse
    0.39
    POSITIVE LOGITS
     initializer
    0.41
     moderator
    0.40
    rasında
    0.40
    OREM
    0.38
    igna
    0.38
     it
    0.38
     my
    0.38
     SISO
    0.38
    ganos
    0.37
    ジナル
    0.37
    Activations Density 0.000%

    No Known Activations