© 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. 5318
    Prev
    Next
    INDEX
    Explanations

    more readable / descriptive / efficient

    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
    am
    0.48
    ころ
    0.46
     ה
    0.46
    ो
    0.44
    ০
    0.42
    anat
    0.42
    um
    0.41
    ampe
    0.41
    en
    0.41
    anak
    0.41
    POSITIVE LOGITS
    യി
    0.42
    Encom
    0.41
     cringe
    0.40
    менно
    0.40
    Ultimately
    0.40
    𝐞
    0.39
    Favorite
    0.39
    trendy
    0.39
    ordable
    0.39
    மொழ
    0.39
    Activations Density 0.433%

    No Known Activations