© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3631
    Prev
    Next
    INDEX
    Explanations

    setopt or search followed by (

    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_5_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
    দ
    0.48
    من
    0.42
    苃
    0.42
    𝙜
    0.42
    codingPath
    0.42
    মধ্যে
    0.42
     elemental
    0.41
    تال
    0.41
    kem
    0.40
    𝗴
    0.40
    POSITIVE LOGITS
    𝑛
    0.52
    נדה
    0.49
    NaN
    0.49
     diri
    0.49
    ɴ
    0.48
    am
    0.48
    Wallet
    0.47
    &-
    0.46
    setTextColor
    0.46
    wipe
    0.45
    Activations Density 0.004%

    No Known Activations