© 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. 5140
    Prev
    Next
    INDEX
    Explanations

    keywords conditional statements

    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
    lijke
    1.70
    েনারেল
    1.51
    なります
    1.46
    দের
    1.45
    ية
    1.43
    thood
    1.41
    ными
    1.39
    ো
    1.38
    আপনি
    1.35
    el
    1.34
    POSITIVE LOGITS
    yh
    1.29
     podľa
    1.27
    न
    1.22
    𝙉
    1.16
    antic
    1.15
    𝙀
    1.14
    ാപാ
    1.13
    ิ
    1.13
    બ
    1.13
     vorhanden
    1.12
    Activations Density 0.112%

    No Known Activations