© 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. 156825
    Prev
    Next
    INDEX
    Explanations

    Deloitte

    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_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
    ről
    1.09
    stwo
    1.05
    να
    1.02
    charged
    1.02
    
    1.01
    니다
    1.00
    ról
    1.00
    bread
    0.96
    お知らせ
    0.96
    bericht
    0.96
    POSITIVE LOGITS
     is
    1.51
    า
    1.47
    та
    1.46
    א
    1.42
    เป็น
    1.39
    ט
    1.34
    ä
    1.23
    是
    1.23
    ל
    1.16
    </td>
    1.15
    Activations Density 0.000%

    No Known Activations