© 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. 127102
    Prev
    Next
    INDEX
    Explanations

    retail media chains

    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
    ী
    0.82
    ant
    0.78
    s
    0.77
    un
    0.70
    al
    0.68
    ال
    0.67
    au
    0.64
    ുണ്ട
    0.63
    old
    0.63
     Anim
    0.63
    POSITIVE LOGITS
    行く
    0.70
     be
    0.64
     və
    0.61
    که
    0.58
    ເລ
    0.58
     เน
    0.57
     pagos
    0.57
     року
    0.57
    կ
    0.57
     powied
    0.56
    Activations Density 0.001%

    No Known Activations