© 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. 200766
    Prev
    Next
    INDEX
    Explanations

    ani / Lan

    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
     conj
    0.40
     yielding
    0.39
    컨
    0.39
     கான்
    0.38
     palin
    0.38
    থিত
    0.38
    丐
    0.37
     ativid
    0.37
     dois
    0.37
    釗
    0.37
    POSITIVE LOGITS
    Sim
    0.41
    mam
    0.39
    物を
    0.39
    Ky
    0.38
     Morocco
    0.37
    Mam
    0.37
    osim
    0.37
     वचन
    0.37
    muted
    0.37
    odim
    0.37
    Activations Density 0.000%

    No Known Activations