© 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. 5558
    Prev
    Next
    INDEX
    Explanations

    Database.Presentation

    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
    ра
    3.27
    मपुर
    2.96
    𝑦
    2.82
    િજા
    2.72
    anterior
    2.64
    ്രി
    2.64
    剂
    2.63
     photocon
    2.58
     eser
    2.58
    ゞ
    2.58
    POSITIVE LOGITS
    ك
    2.63
    th
    2.58
    nesday
    2.31
    させ
    2.30
    st
    2.28
    させて
    2.28
    #######
    2.27
    gies
    2.24
    させる
    2.24
    शील
    2.22
    Activations Density 0.000%

    No Known Activations