© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13874
    Prev
    Next
    INDEX
    Explanations

    driving conditions and metrics

    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_13_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
    Purch
    0.39
    purch
    0.38
    lack
    0.35
    Allora
    0.35
    ounsel
    0.33
    𝓢
    0.33
    Fecha
    0.32
    archivo
    0.32
    Ю
    0.32
     celebratory
    0.32
    POSITIVE LOGITS
     össze
    0.37
    िलायंस
    0.37
     spolu
    0.35
    న్స్‌
    0.35
     原子
    0.35
     tervez
    0.35
     jazdy
    0.34
     hoofd
    0.34
     shrug
    0.34
     perturb
    0.34
    Activations Density 0.063%

    No Known Activations