© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31072
    Prev
    Next
    INDEX
    Explanations

    old man names

    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_31_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
     प्रिय
    0.40
     trúc
    0.38
    皰
    0.38
     taget
    0.38
    রাম
    0.38
     없어
    0.38
    RIER
    0.37
     Guzmán
    0.37
     বিন্দু
    0.37
    齧
    0.37
    POSITIVE LOGITS
     একজন
    0.44
    একজন
    0.43
     unui
    0.41
     isang
    0.40
     einen
    0.40
     eines
    0.39
    ்துற
    0.38
    ิศ
    0.37
     an
    0.37
     a
    0.36
    Activations Density 0.007%

    No Known Activations