© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90662
    Prev
    Next
    INDEX
    Explanations

    Ahmad, Palace, MPC, alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ف
    1.19
    ו
    1.04
    س
    1.02
    م
    1.00
    ج
    0.87
    ח
    0.84
    ك
    0.82
    ע
    0.82
    ↵↵
    0.80
    ম
    0.79
    POSITIVE LOGITS
    _
    0.89
    р
    0.80
    ່ນ
    0.71
     Віль
    0.71
    ների
    0.70
    ᱸ
    0.70
    crumb
    0.69
    handmade
    0.69
    arsenic
    0.68
    ᆹ
    0.68
    Activations Density 0.008%

    No Known Activations