© 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. 166578
    Prev
    Next
    INDEX
    Explanations

    on

    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
    倾向
    0.36
     reen
    0.36
     setan
    0.35
    账号
    0.35
     حساب
    0.35
    psin
    0.35
     Rouse
    0.34
    眞
    0.34
     beneficio
    0.34
    楹
    0.34
    POSITIVE LOGITS
     medically
    0.42
     halfway
    0.40
    ครัว
    0.38
     médicale
    0.38
     نقص
    0.37
     MEDICAL
    0.36
    MEDICAL
    0.36
     medical
    0.36
     अस्पताल
    0.35
     الطب
    0.35
    Activations Density 0.004%

    No Known Activations