© 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. 5139
    Prev
    Next
    INDEX
    Explanations

    descriptive suffixes and intensifiers

    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
    r
    0.51
    utorial
    0.48
     readFile
    0.46
    e
    0.46
    rion
    0.45
     منہ
    0.43
    ar
    0.42
    ں
    0.42
    ന്നും
    0.41
    nj
    0.41
    POSITIVE LOGITS
     그러
    0.41
    ‌ترین
    0.40
     vanligt
    0.40
    猾
    0.39
    THING
    0.39
    зирован
    0.39
     زیادی
    0.38
     cations
    0.38
     сведения
    0.38
    allergenic
    0.38
    Activations Density 0.100%

    No Known Activations