© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164361
    Prev
    Next
    INDEX
    Explanations

    strike up conversations

    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_13_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
    くて
    0.63
    klop
    0.62
     htim
    0.61
    ෛ
    0.60
     Ettha
    0.59
    ပို
    0.58
    ceğ
    0.57
    ేక
    0.57
    ږئ
    0.57
    هاي
    0.57
    POSITIVE LOGITS
    ร
    0.59
     photographs
    0.54
    *
    0.54
    \*
    0.53
    Р
    0.52
     electron
    0.52
     paintings
    0.50
     jewelry
    0.50
     al
    0.49
    **
    0.49
    Activations Density 0.000%

    No Known Activations