© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36191
    Prev
    Next
    INDEX
    Explanations

    multiple ways

    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_31_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
     bul
    0.35
     palm
    0.34
    シル
    0.34
    Ổ
    0.34
    ổ
    0.34
    bag
    0.33
    irp
    0.32
     کیف
    0.32
     mug
    0.31
     Abu
    0.31
    POSITIVE LOGITS
     BELOW
    0.40
     MOTION
    0.38
    Неза
    0.38
    侘
    0.37
    Below
    0.35
    knię
    0.35
     asalamualaikum
    0.35
     Bevan
    0.35
    жні
    0.34
     ฉาก
    0.33
    Activations Density 0.011%

    No Known Activations