© 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. 5570
    Prev
    Next
    INDEX
    Explanations

    writes "only", "a", "output", "now", "can"

    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
    AS
    0.86
    스
    0.84
    AL
    0.81
    스럽
    0.81
    ์
    0.80
    ੀ
    0.79
    有利于
    0.78
    ת
    0.76
    cellaneous
    0.75
    지난
    0.75
    POSITIVE LOGITS
    েন
    0.78
    lapping
    0.78
    ulously
    0.74
     semblance
    0.74
    łada
    0.72
    r
    0.71
    ^{*}\
    0.69
    ulence
    0.69
    がら
    0.68
    בים
    0.68
    Activations Density 0.717%

    No Known Activations