© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150940
    Prev
    Next
    INDEX
    Explanations

    github

    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
    olen
    0.44
    .'),
    0.39
    \%),
    0.38
    ግራ
    0.38
     giro
    0.37
     гі
    0.37
    GITHUB
    0.37
    说是
    0.37
    orsanız
    0.37
     गिरी
    0.36
    POSITIVE LOGITS
    s
    0.69
    sPath
    0.47
    sht
    0.43
    ᅩ
    0.43
    ો
    0.41
     *@
    0.40
    ی
    0.38
    ង្
    0.38
     iam
    0.38
     Со
    0.38
    Activations Density 0.001%

    No Known Activations