© 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. 35127
    Prev
    Next
    INDEX
    Explanations

    quotations and 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_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
     ['(?
    0.02
    CriteriaUtils
    0.02
    stvu
    0.02
    壹章
    0.02
    استشهاد
    0.02
    সৌ
    0.02
    洿
    0.02
    叁章
    0.02
     зарубе
    0.02
    INTa
    0.02
    POSITIVE LOGITS
    0.03
     Bach
    0.02
     "
    0.02
     to
    0.02
     M
    0.02
     the
    0.02
     Fraction
    0.02
     I
    0.02
     lifted
    0.02
     partially
    0.02
    Activations Density 0.010%

    No Known Activations