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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5517
    Prev
    Next
    INDEX
    Explanations

    latex article documentclass

    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
    ра
    3.20
    тоў
    2.80
    en
    2.55
    leiter
    2.49
    asjon
    2.46
    𝗖
    2.43
    ни
    2.40
     ballast
    2.38
     conseguir
    2.35
    ина
    2.31
    POSITIVE LOGITS
    ྱི་
    2.52
    儡
    2.48
    نسب
    2.27
    不仅仅
    2.27
     discredit
    2.25
    mente
    2.25
     fief
    2.23
     discretion
    2.19
     emulate
    2.17
     ListTile
    2.14
    Activations Density 0.000%

    No Known Activations