© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1493
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    is
    2.92
     tetap
    2.45
     accommodate
    2.35
    𝙤
    2.28
    ات
    2.27
    oppable
    2.27
    ի
    2.25
     인해
    2.24
    ם
    2.23
     chữ
    2.20
    POSITIVE LOGITS
    ===============
    2.23
    这也是
    2.19
    ซ์
    2.14
    ж
    2.08
    ब्रिट
    2.04
     numa
    2.03
    قدم
    2.02
    Ĺ
    2.02
     begitu
    1.99
    फाइनल
    1.99
    Activations Density 0.012%

    No Known Activations