© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 4886
    Prev
    Next
    INDEX
    Explanations

    Capri, Capra, rich

    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
    ➜
    1.83
    hold
    1.77
    usion
    1.73
    টিয়
    1.67
    ある
    1.66
     ane
    1.66
     hela
    1.65
    okol
    1.65
     touchdown
    1.63
    𝓵
    1.63
    POSITIVE LOGITS
     rodzaju
    2.27
     منك
    2.22
     인해
    2.22
    gathering
    2.19
    ят
    2.16
    கல்
    2.15
    وأ
    2.12
    می
    2.09
    اس
    2.07
    च
    2.07
    Activations Density 0.001%

    No Known Activations