© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235914
    Prev
    Next
    INDEX
    Explanations

    Individual

    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_46_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
     כמ
    0.40
     ڕ
    0.38
     colère
    0.37
    று
    0.36
     ত্বক
    0.36
    ಂಕ
    0.36
    delay
    0.36
     delay
    0.36
     extrapol
    0.35
    耽
    0.35
    POSITIVE LOGITS
     individuals
    0.63
    individuals
    0.63
     individuos
    0.62
    Individuals
    0.61
     Individuals
    0.61
     individus
    0.57
     indivíduos
    0.48
    個
    0.47
     افراد
    0.45
     индивидуа
    0.45
    Activations Density 0.002%

    No Known Activations