© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5284
    Prev
    Next
    INDEX
    Explanations

    profanity or negative exclamations

    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
    ل
    3.81
     puluh
    2.55
     tunt
    2.52
    turquoise
    2.50
    寄り
    2.49
    progressBar
    2.47
    ون
    2.46
    єш
    2.41
    l
    2.39
     जून
    2.38
    POSITIVE LOGITS
    ujudkan
    2.49
    િયા
    2.36
    িতে
    2.32
    دد
    2.21
    ח
    2.19
    й
    2.16
    dashboard
    2.14
    нибудь
    2.13
    daten
    2.12
    \{
    2.09
    Activations Density 0.026%

    No Known Activations