© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139717
    Prev
    Next
    INDEX
    Explanations

    `@` followed by username or identifier

    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_37_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
    隻
    0.42
    闷
    0.41
     bem
    0.36
     Voc
    0.36
    фіка
    0.36
    toDouble
    0.35
     سبيل
    0.35
     еди
    0.34
    悶
    0.34
    )](
    0.33
    POSITIVE LOGITS
    AUS
    0.47
     nuevo
    0.43
    aus
    0.41
     hogar
    0.39
    pay
    0.39
     scrive
    0.38
    गृह
    0.38
     hometown
    0.37
     اطلا
    0.37
     Tate
    0.37
    Activations Density 0.000%

    No Known Activations