© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232079
    Prev
    Next
    INDEX
    Explanations

    di/de followed by verbs

    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_6_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
     l
    1.20
    ן
    1.09
    t
    1.03
    ত
    1.03
    야
    0.98
     t
    0.92
     se
    0.91
     er
    0.91
    রাও
    0.91
     r
    0.91
    POSITIVE LOGITS
    ม
    1.08
    isShow
    0.95
    ಧಿಕ
    0.89
    ad
    0.88
    筱
    0.84
    Empleado
    0.84
    拉斯
    0.84
    参加
    0.83
    属性
    0.83
    r
    0.83
    Activations Density 0.000%

    No Known Activations