© 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. 7281
    Prev
    Next
    INDEX
    Explanations

    nuanced topic

    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
    cego
    1.29
    𝖊
    1.18
    '$
    1.16
    다음
    1.14
    ve
    1.11
    сль
    1.07
    𝖔
    1.05
    temper
    1.05
    ]})
    1.05
     Nombre
    1.04
    POSITIVE LOGITS
    л
    1.17
    PING
    1.10
     Такой
    1.10
     oud
    1.09
     gide
    1.08
     wrists
    1.08
     sided
    1.07
     vidare
    1.06
     зрения
    1.06
     giants
    1.06
    Activations Density 0.024%

    No Known Activations