© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45646
    Prev
    Next
    INDEX
    Explanations

    swirling around

    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_3_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
    0.86
     swap
    0.71
     sw
    0.70
    </b>
    0.68
    og
    0.66
     swapping
    0.64
    as
    0.64
    4
    0.63
     riches
    0.63
    ?
    0.63
    POSITIVE LOGITS
    м
    0.96
    ни
    0.75
    de
    0.73
    <0x80>
    0.71
    ве
    0.70
    របស់
    0.66
    ين
    0.65
    ることが
    0.64
    ى
    0.64
     كه
    0.64
    Activations Density 0.000%

    No Known Activations