© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149349
    Prev
    Next
    INDEX
    Explanations

    names or titles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     just
    0.71
     vừa
    0.57
     juste
    0.51
     appena
    0.48
     *
    0.46
     เข
    0.46
     जस्ट
    0.46
     JUST
    0.45
    just
    0.44
     예
    0.44
    POSITIVE LOGITS
    Miller
    0.50
    Measure
    0.46
    Really
    0.46
    Shall
    0.46
    Five
    0.45
    Jersey
    0.44
    Annie
    0.44
    Ste
    0.43
    Studio
    0.43
    Steel
    0.43
    Activations Density 0.001%

    No Known Activations