© 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. 3470
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
    চিৎ
    0.22
    ки
    0.21
    𝗎
    0.20
    siniz
    0.20
     yere
    0.20
    𝐨
    0.19
    sman
    0.19
    ো
    0.19
     kuri
    0.19
    යින්
    0.19
    POSITIVE LOGITS
    mathbb
    0.22
    下面
    0.20
     sabor
    0.17
    aligned
    0.17
     Ngoài
    0.17
    ので
    0.17
     polity
    0.17
    quad
    0.16
    d
    0.16
     वाला
    0.16
    Activations Density 0.458%

    No Known Activations