© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 148532
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
    u
    0.81
    U
    0.75
    ü
    0.59
     u
    0.51
    𝐮
    0.47
    ու
    0.46
    su
    0.44
    Su
    0.43
    Lu
    0.43
     Lu
    0.43
    POSITIVE LOGITS
     UCL
    0.84
     UC
    0.76
     UCLA
    0.67
    uc
    0.61
     uc
    0.58
    UC
    0.53
     Uc
    0.52
     UCS
    0.49
     duc
    0.47
     comp
    0.47
    Activations Density 0.017%

    No Known Activations