© 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. 6402
    Prev
    Next
    INDEX
    Explanations

    all of the

    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
    󠁣
    2.58
     Expr
    2.53
    ท์
    2.49
    t
    2.44
    おり
    2.28
    quiera
    2.18
    cargar
    2.18
    त
    2.17
    其中的
    2.16
    nen
    2.15
    POSITIVE LOGITS
    ات
    2.85
    बॉल
    2.75
    سي
    2.49
     expend
    2.43
    𝙤
    2.41
     föl
    2.39
    هم
    2.35
    ச்சூழ
    2.31
    ेप
    2.31
     ushered
    2.30
    Activations Density 0.038%

    No Known Activations