© 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. 147733
    Prev
    Next
    INDEX
    Explanations

    say numbers

    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
    …</
    0.49
     અલ
    0.46
    nofollow
    0.45
    चाप
    0.44
    Chaer
    0.44
    \...
    0.44
    five
    0.42
    ).}
    0.42
    ToOne
    0.42
    ]&
    0.42
    POSITIVE LOGITS
    ٣
    0.56
    □
    0.55
     ____________
    0.54
     _____________
    0.52
    ۳
    0.52
    9
    0.51
    6
    0.49
     ________
    0.48
     ______
    0.47
     _______
    0.47
    Activations Density 0.002%

    No Known Activations