© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224770
    Prev
    Next
    INDEX
    Explanations

    reciprocal action, quid pro quo, agreements

    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_10_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
    in
    0.55
    н
    0.52
    א
    0.52
    is
    0.50
    ن
    0.49
    im
    0.48
    n
    0.46
    on
    0.42
    imizi
    0.41
    न
    0.40
    POSITIVE LOGITS
     reciprocal
    0.44
     with
    0.36
     soap
    0.36
     ERIC
    0.36
     \$
    0.35
     ART
    0.35
     jasa
    0.35
     FREE
    0.34
     reciproc
    0.34
     polka
    0.34
    Activations Density 0.009%

    No Known Activations