© 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. 58308
    Prev
    Next
    INDEX
    Explanations

    meg

    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
    ees
    0.50
    ein
    0.45
    潛行
    0.43
    កាន់
    0.42
    𝘵
    0.41
    ection
    0.41
    ICLES
    0.40
    chées
    0.40
     keiner
    0.39
     ছোট
    0.39
    POSITIVE LOGITS
    o
    0.85
    ad
    0.66
    aba
    0.54
    اب
    0.54
    aj
    0.53
    ati
    0.52
    adah
    0.52
    ase
    0.51
    adb
    0.50
     terrestrial
    0.50
    Activations Density 0.000%

    No Known Activations