© 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. 8591
    Prev
    Next
    INDEX
    Explanations

    serpentine

    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
    ל
    2.76
    ⅜
    2.58
    হাম্ম
    2.56
    CONNECTION
    2.54
    specially
    2.44
    ্ম্ম
    2.42
    ɦ
    2.41
    বি
    2.41
    𝑎
    2.40
    𝑣
    2.37
    POSITIVE LOGITS
    ный
    2.81
     courtes
    2.78
    けど
    2.67
    
    2.67
     overloading
    2.64
     courants
    2.60
     cuc
    2.59
    धरी
    2.58
    螂
    2.56
    cellent
    2.54
    Activations Density 0.031%

    No Known Activations