© 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. 5543
    Prev
    Next
    INDEX
    Explanations

    verb followed by preposition/conjunction

    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
    i
    0.61
    ف
    0.59
    க
    0.58
    я
    0.57
    ك
    0.56
    про
    0.52
    ки
    0.52
    رو
    0.52
    ی
    0.51
    мий
    0.51
    POSITIVE LOGITS
    된
    0.52
     stony
    0.51
     Oceania
    0.51
     MSRP
    0.50
    ྗ
    0.50
     lite
    0.50
    ందించ
    0.50
     JSTOR
    0.49
    <unused92>
    0.49
    rition
    0.49
    Activations Density 0.831%

    No Known Activations