© 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. 5103
    Prev
    Next
    INDEX
    Explanations

    as of [date/time]

    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
    arul
    2.71
    ⃛
    2.56
    ar
    2.51
    ু
    2.39
    ли
    2.31
    el
    2.22
    NSLog
    2.15
    <0x80>
    2.13
    ן
    2.10
    ন
    2.01
    POSITIVE LOGITS
    𝔰
    2.41
    𝔱
    2.40
    𝔬
    2.25
    ی
    2.21
     निशाना
    2.11
    𝘻
    1.97
    𝘦
    1.96
     getContentPane
    1.95
    𝘴
    1.94
    𝔪
    1.92
    Activations Density 0.007%

    No Known Activations