© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3539
    Prev
    Next
    INDEX
    Explanations

    CLOSER

    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_5_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
    om
    0.40
    ع
    0.39
    ió
    0.39
    p
    0.38
    z
    0.37
    d
    0.36
    tir
    0.35
    ut
    0.35
    lere
    0.35
    y
    0.34
    POSITIVE LOGITS
    ங்கிணை
    0.66
     GestureDetector
    0.42
     discerned
    0.41
    ENING
    0.41
     discriminated
    0.40
     alight
    0.40
    UserDefaults
    0.40
    sembling
    0.39
     defaultdict
    0.39
    ຈັດສົ່ງ
    0.39
    Activations Density 2.963%

    No Known Activations