© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121936
    Prev
    Next
    INDEX
    Explanations

    names and titles ending with specific punctuation

    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_3_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
     in
    0.91
     worden
    0.70
    t
    0.70
     WHO
    0.65
     einzel
    0.64
     reader
    0.64
    li
    0.63
    ının
    0.63
     /=
    0.63
     GROW
    0.62
    POSITIVE LOGITS
    ب
    1.06
    یس
    1.03
    ج
    1.02
    ق
    1.02
    یک
    0.98
    ک
    0.95
    ᱐
    0.89
    О
    0.88
    ول
    0.86
    ପ
    0.84
    Activations Density 0.001%

    No Known Activations