© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4803
    Prev
    Next
    INDEX
    Explanations

    windswept landscapes and objects

    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
    jest
    2.57
     rectify
    2.52
     हाँ
    2.49
     diagonalization
    2.42
     pago
    2.41
    要知道
    2.39
    д
    2.35
    fontsize
    2.34
    ം
    2.34
    ક્ષ
    2.34
    POSITIVE LOGITS
    t
    3.53
    ب
    3.01
    蜢
    2.86
    یثیت
    2.52
    cA
    2.52
    \,.
    2.52
    siniz
    2.51
    ուր
    2.45
    ない
    2.34
     dashing
    2.30
    Activations Density 0.058%

    No Known Activations