© 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. 220509
    Prev
    Next
    INDEX
    Explanations

    URLs with identifiers

    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
     चुक
    0.38
     анг
    0.38
     LUCKY
    0.38
     количе
    0.37
    स्टार
    0.37
    *\
    0.37
     ইংরেজি
    0.37
    য়নের
    0.36
     Анг
    0.35
     Lucky
    0.35
    POSITIVE LOGITS
    etric
    0.52
    roweak
    0.38
    wee
    0.37
    wa
    0.37
    父
    0.37
     wag
    0.36
     coalition
    0.36
    race
    0.36
    abbat
    0.36
     wa
    0.35
    Activations Density 0.000%

    No Known Activations