© 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. 5507
    Prev
    Next
    INDEX
    Explanations

    file extensions and components

    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
    ELLOW
    2.05
     nozzles
    2.03
    ال
    1.95
    obstacle
    1.88
    styling
    1.86
     CRUD
    1.82
    껭
    1.82
    arrera
    1.79
    ޘ
    1.79
     puffy
    1.76
    POSITIVE LOGITS
    an
    2.43
     그러면
    1.85
    のは
    1.85
    িশীল
    1.84
     ganz
    1.75
    ',
    1.69
    هههه
    1.68
    >
    1.65
    त
    1.65
    ં
    1.63
    Activations Density 0.038%

    No Known Activations