© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66273
    Prev
    Next
    INDEX
    Explanations

    refugee and PR card

    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
    灲
    0.41
     yer
    0.39
     sít
    0.37
    化妆
    0.37
    𓏧
    0.37
    慓
    0.36
     ters
    0.36
     invit
    0.36
    قان
    0.36
    
    0.36
    POSITIVE LOGITS
     Slave
    0.55
     refugee
    0.46
    Slave
    0.43
     slave
    0.43
    ртом
    0.43
    slave
    0.41
    arctic
    0.40
     hue
    0.40
    HUD
    0.39
     وسلم
    0.38
    Activations Density 0.017%

    No Known Activations