© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6643
    Prev
    Next
    INDEX
    Explanations

    hard

    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
    mtr
    2.09
    HING
    2.07
    ment
    1.96
    ])))
    1.91
     uneas
    1.85
    ("-"*
    1.84
     exert
    1.82
     entra
    1.80
     الكثير
    1.74
    AWSJavaScriptSDK
    1.73
    POSITIVE LOGITS
    𝘨
    2.35
    𝘵
    2.04
    𝘯
    2.02
    犸
    1.97
    要
    1.96
    ь
    1.89
    𝘻
    1.85
    ੀ
    1.81
    רת
    1.74
    eo
    1.74
    Activations Density 0.081%

    No Known Activations