© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 2-GEMMASCOPE-2-TRANSCODER-262K
    4. 59463
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    اً
    1.38
    اں
    1.24
    ا
    1.18
    اک
    1.13
    از
    0.99
    ového
    0.95
    ामध्ये
    0.95
    ,
    0.94
    व्या
    0.93
    取り付け
    0.91
    POSITIVE LOGITS
     legitim
    1.30
     reorgan
    1.13
    6
    1.12
     of
    1.09
     angered
    1.04
    NI
    1.03
     jeopard
    1.02
     for
    1.02
    জ
    1.00
    }];
    0.99
    Activations Density 0.000%

    No Known Activations