© 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. 3717
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    at
    0.31
     ilk
    0.31
    c
    0.30
    im
    0.28
    ൂര
    0.28
     tels
    0.27
     szk
    0.27
    bags
    0.27
    ઓની
    0.27
     erste
    0.27
    POSITIVE LOGITS
    <unused302>
    0.35
    াড়াও
    0.34
     purely
    0.33
    <unused542>
    0.33
     Cactus
    0.32
    <unused702>
    0.31
    <unused1700>
    0.31
    𒐸
    0.31
     disappointing
    0.30
     сильно
    0.30
    Activations Density 0.470%

    No Known Activations