© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204436
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    퇸
    0.40
     episod
    0.37
     substitu
    0.36
    栘
    0.36
    ុស
    0.36
    캿
    0.36
     എന്നാല്‍
    0.35
     legyen
    0.35
     transforma
    0.35
     organizada
    0.35
    POSITIVE LOGITS
    ig
    0.38
    b
    0.36
     通常
    0.36
    密切
    0.36
     উদ্বেগ
    0.36
     bài
    0.35
    ich
    0.35
    '$.
    0.35
     psychological
    0.34
     सामान्य
    0.34
    Activations Density 0.000%

    No Known Activations