© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8219
    Prev
    Next
    INDEX
    Explanations

    German words and phrases

    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_40_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
    Task
    0.48
     Task
    0.46
     given
    0.40
     TASK
    0.38
     Tasks
    0.38
     انها
    0.37
    </tr>
    0.37
    Given
    0.37
    ady
    0.36
     tâche
    0.36
    POSITIVE LOGITS
    ktron
    0.39
    ರವಾಗಿ
    0.39
     đạo
    0.38
     tripping
    0.37
    кономски
    0.36
    拍
    0.35
    CCCN
    0.34
    breakers
    0.34
     huynh
    0.34
     hurried
    0.34
    Activations Density 0.035%

    No Known Activations