© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146716
    Prev
    Next
    INDEX
    Explanations

    must/should

    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_59_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
     seharusnya
    0.49
    ارات
    0.37
     normalement
    0.36
    éraire
    0.35
     mor
    0.34
    mor
    0.33
    рија
    0.33
    끽
    0.33
    шлай
    0.32
     sebenarnya
    0.32
    POSITIVE LOGITS
     must
    2.91
    must
    2.67
     Must
    2.63
    Must
    2.58
    必须
    2.38
     phải
    2.34
     måste
    2.19
    ต้อง
    2.16
    MUST
    2.16
     deben
    2.13
    Activations Density 0.000%

    No Known Activations