© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7414
    Prev
    Next
    INDEX
    Explanations

    ```textjson or xml following rb or POST```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ів
    2.24
    িট
    2.11
    as
    1.99
     pelos
    1.86
    t
    1.86
    費
    1.80
     sağlı
    1.78
     Pada
    1.77
    жений
    1.77
    iforn
    1.77
    POSITIVE LOGITS
    𝐫
    2.17
     crux
    2.10
    ج
    2.07
    Conversely
    1.91
     estaven
    1.90
    glVertex
    1.90
    ો
    1.90
     voxel
    1.87
     $|
    1.86
    Occasionally
    1.84
    Activations Density 0.108%

    No Known Activations