© 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. 162827
    Prev
    Next
    INDEX
    Explanations

    return ({

    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
     রাজধান
    0.37
     си
    0.36
    getValue
    0.35
     Focusing
    0.35
    ৃতি
    0.35
    VICES
    0.35
    暝
    0.34
    injlim
    0.34
    ildet
    0.34
    opt
    0.34
    POSITIVE LOGITS
     촉
    0.41
     PDF
    0.38
     lakeside
    0.38
    썬
    0.38
     pile
    0.37
     sunshine
    0.37
     Shine
    0.37
     involve
    0.36
     竹
    0.36
     crest
    0.36
    Activations Density 0.000%

    No Known Activations