© 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. 59954
    Prev
    Next
    INDEX
    Explanations

    writing cards

    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
     completed
    0.45
     Completed
    0.40
     he
    0.39
    寛
    0.39
     nemat
    0.38
    诬
    0.38
    completed
    0.37
     finished
    0.37
     pleas
    0.37
     powered
    0.37
    POSITIVE LOGITS
     die
    0.52
    ~
    0.48
     ~~
    0.46
     ~
    0.45
    die
    0.45
     pat
    0.44
    റ്റ്‌വർ
    0.42
    ~~
    0.40
    ~~~
    0.39
    Pat
    0.39
    Activations Density 0.001%

    No Known Activations