© 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. 53906
    Prev
    Next
    INDEX
    Explanations

    news sources NPR, BBC

    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
     CRIM
    0.37
    续
    0.35
     irgend
    0.35
     Zeiten
    0.34
    activer
    0.34
    續
    0.34
     leisten
    0.33
    +](
    0.33
    xref
    0.32
    obaan
    0.32
    POSITIVE LOGITS
     વર્
    0.36
    Raising
    0.36
    振り
    0.35
     Marking
    0.32
     завтра
    0.32
     shar
    0.32
    geois
    0.31
     hedge
    0.31
     sharpness
    0.31
     VV
    0.31
    Activations Density 0.000%

    No Known Activations