Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3743
    Prev
    Next
    INDEX
    Explanations

    physical media formats

    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
    да
    0.68
    𝐝
    0.62
    ξε
    0.59
     curtailed
    0.58
    ش
    0.55
    يد
    0.55
    ين
    0.54
    ার
    0.53
    даги
    0.53
    ain
    0.53
    POSITIVE LOGITS
    ről
    0.49
    music
    0.47
     осіб
    0.44
     относятся
    0.43
    lí
    0.42
    cid
    0.42
    евна
    0.40
    lls
    0.40
    ၎
    0.40
    蓣
    0.40
    Activations Density 0.060%

    No Known Activations