© 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. 49953
    Prev
    Next
    INDEX
    Explanations

    product tour details

    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
    mousePressed
    0.36
    婹
    0.34
     RAL
    0.33
     গের
    0.33
     accompanying
    0.32
     stains
    0.30
     ligature
    0.29
    ompany
    0.29
     एनीमिया
    0.29
     accompany
    0.29
    POSITIVE LOGITS
     برو
    0.32
    '],'
    0.30
    Brain
    0.29
    Stern
    0.29
     Jazeera
    0.29
    రణ
    0.29
     conferences
    0.29
    ška
    0.29
    brane
    0.28
     brag
    0.28
    Activations Density 0.116%

    No Known Activations