© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18060
    Prev
    Next
    INDEX
    Explanations

    mode, context, or specific situation

    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_34_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
    ಕರಣ
    0.40
     മാര്‍
    0.40
     dibuka
    0.39
     څخه
    0.38
    繹
    0.38
    뻗
    0.38
     ጋር
    0.37
    ಕ್ರ
    0.36
    垍
    0.36
     而
    0.36
    POSITIVE LOGITS
     وفي
    0.47
     mode
    0.38
     manner
    0.38
     hine
    0.38
    ющем
    0.37
    ებში
    0.37
     целях
    0.37
     році
    0.37
     Bare
    0.35
     представители
    0.35
    Activations Density 0.285%

    No Known Activations