© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58698
    Prev
    Next
    INDEX
    Explanations

    couchdb

    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_2_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
    та
    1.48
    س
    1.39
    માં
    1.34
    ਾ
    1.27
    ن
    1.21
    า
    1.20
    ק
    1.16
    نا
    1.05
    ρα
    1.04
     électron
    1.04
    POSITIVE LOGITS
     with
    1.55
     on
    1.10
    de
    0.99
     by
    0.98
     metam
    0.94
    K
    0.91
     for
    0.91
    with
    0.89
     duet
    0.89
    м
    0.89
    Activations Density 0.000%

    No Known Activations