© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156378
    Prev
    Next
    INDEX
    Explanations

    talk or speak

    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
    ><?
    0.41
     Сак
    0.40
     Sarat
    0.40
     Emm
    0.39
    ట్స్‌
    0.39
     Em
    0.38
    云
    0.38
    อัล
    0.38
     recom
    0.37
     incom
    0.37
    POSITIVE LOGITS
     लो
    0.41
     rod
    0.40
    neh
    0.39
     처
    0.38
    nea
    0.37
     weitere
    0.37
     भुव
    0.36
     άλλα
    0.36
    Lo
    0.36
    mw
    0.36
    Activations Density 0.000%

    No Known Activations