© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92583
    Prev
    Next
    INDEX
    Explanations

    sou

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     이루
    0.74
     이
    0.49
    떠
    0.47
    อน
    0.41
    ılmaz
    0.37
    ัง
    0.36
     disproportion
    0.33
    gen
    0.33
     DO
    0.33
    อิ
    0.33
    POSITIVE LOGITS
    な
    1.71
     na
    1.59
     на
    1.58
    為
    1.23
    为
    1.17
     な
    1.16
     होता
    1.14
     trên
    1.05
    なさ
    1.02
     på
    1.00
    Activations Density 0.001%

    No Known Activations