© 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. 90265
    Prev
    Next
    INDEX
    Explanations

    People and names

    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
    前
    0.61
    rieg
    0.56
    孕
    0.54
    的和
    0.54
     reeks
    0.53
     it
    0.52
     вече
    0.52
    的就是
    0.52
     учетом
    0.52
    ries
    0.51
    POSITIVE LOGITS
    ر
    0.73
    ad
    0.72
    ות
    0.69
    した
    0.67
    ivores
    0.65
    r
    0.65
    ский
    0.65
    ির
    0.62
    ية
    0.61
    ер
    0.60
    Activations Density 0.001%

    No Known Activations