© 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. 6373
    Prev
    Next
    INDEX
    Explanations

    ocean(s) followed by descriptions

    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
    ன்
    2.63
    愎
    2.37
    zość
    2.32
    kes
    2.17
    𝐺
    2.08
     TSC
    2.08
    mere
    2.06
    𝑠
    2.06
     tahap
    2.02
    irical
    2.02
    POSITIVE LOGITS
    at
    3.16
    یثیت
    2.70
     طریق
    2.52
     perfused
    2.49
     potrzeby
    2.47
    скія
    2.47
    atı
    2.41
    л
    2.41
    िक
    2.38
    ᴠ
    2.35
    Activations Density 0.025%

    No Known Activations