© 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. 41345
    Prev
    Next
    INDEX
    Explanations

    cobots

    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
    t
    1.22
    та
    0.86
    ون
    0.83
    en
    0.79
    s
    0.79
    <0x80>
    0.71
    ad
    0.70
    al
    0.69
    س
    0.68
    ె
    0.68
    POSITIVE LOGITS
     waktu
    0.77
    ı
    0.65
    টি
    0.63
    ORE
    0.63
    ید
    0.63
    ando
    0.63
     czasu
    0.63
    เวลา
    0.62
    i
    0.60
    ั
    0.59
    Activations Density 0.001%

    No Known Activations