© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79091
    Prev
    Next
    INDEX
    Explanations

    There now

    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
     cazul
    0.43
     trusty
    0.41
    <unused240>
    0.41
     ništa
    0.40
     मंज
    0.38
     голе
    0.38
    !!!!!!!
    0.38
    !!!!!!
    0.38
     CaO
    0.38
    !!!!!!!!
    0.37
    POSITIVE LOGITS
    wells
    0.36
    making
    0.36
    izability
    0.36
    statics
    0.36
    慗
    0.35
    inine
    0.35
     making
    0.33
    vod
    0.33
    z
    0.33
    soldiers
    0.33
    Activations Density 0.001%

    No Known Activations