© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3384
    Prev
    Next
    INDEX
    Explanations

    langchain

    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_5_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
    in
    1.73
    ियल
    1.58
     бы
    1.50
    ```
    1.47
    াল
    1.44
    (/
    1.43
    𝚘
    1.40
    된
    1.39
    료
    1.37
     (`
    1.36
    POSITIVE LOGITS
    daki
    2.21
    পাঁ
    1.82
     পাঁ
    1.80
    ました
    1.78
     ondas
    1.77
    ടങ്ങ
    1.77
     hips
    1.76
     creatures
    1.74
     tagName
    1.72
     lysosomes
    1.72
    Activations Density 0.000%

    No Known Activations