© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199724
    Prev
    Next
    INDEX
    Explanations

    programmed

    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_50_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
     массо
    0.37
     pace
    0.37
    縞
    0.37
    τως
    0.36
    베
    0.36
    있는
    0.36
    ωνα
    0.36
     Nascimento
    0.36
    ერის
    0.36
    또
    0.35
    POSITIVE LOGITS
    Marsh
    0.37
    شود
    0.37
     Ship
    0.36
    otechn
    0.35
    ONENT
    0.35
    ্রো
    0.35
    outines
    0.34
     незале
    0.34
    шы
    0.34
     throm
    0.34
    Activations Density 0.004%

    No Known Activations