© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64041
    Prev
    Next
    INDEX
    Explanations

    It is with

    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_41_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
    ంచరీలు
    0.42
    贰
    0.38
     متع
    0.36
     अनुर
    0.35
    뀨
    0.35
    ঠি
    0.34
     bonnet
    0.34
    ---------*/
    0.34
    ाइट
    0.33
     utilizzando
    0.33
    POSITIVE LOGITS
    With
    1.84
     With
    1.77
    with
    1.70
     with
    1.65
     avec
    1.61
     dengan
    1.53
     WITH
    1.48
     với
    1.45
    WITH
    1.43
     Avec
    1.42
    Activations Density 0.003%

    No Known Activations