© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102144
    Prev
    Next
    INDEX
    Explanations

    Start is called

    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_16_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
     princess
    0.54
    abilidad
    0.50
    第一
    0.49
    lighet
    0.47
    ג
    0.46
    y
    0.46
     unworthy
    0.46
     risk
    0.46
    Symptoms
    0.46
    elihood
    0.46
    POSITIVE LOGITS
    ຂໍ້ມູນ
    0.60
     дети
    0.56
    sourceEncoding
    0.56
     पढ़ाई
    0.53
     માહિતી
    0.53
     dữ
    0.52
     माहिती
    0.51
     అంది
    0.51
     程
    0.51
     далеко
    0.51
    Activations Density 0.002%

    No Known Activations