© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58200
    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
    ?
    1.04
    .</
    0.98
    ر
    0.97
    _
    0.96
    ৩
    0.96
    ن
    0.95
    },
    0.95
    </
    0.95
     precondition
    0.93
    stion
    0.92
    POSITIVE LOGITS
    지
    1.19
    ють
    1.14
    ى
    1.13
    다
    1.08
    어
    1.07
    า
    1.06
    ী
    1.00
    ਾ
    0.96
    ή
    0.94
    的样子
    0.93
    Activations Density 0.000%

    No Known Activations