© 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
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4674
    Prev
    Next
    INDEX
    Explanations

    friend, amigo, 谊

    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
    ll
    2.96
    nde
    2.43
    𝐮
    2.23
    ve
    2.19
    𝐭
    2.18
    <0x80>
    2.16
    вой
    2.11
    lll
    2.09
    ل
    2.07
    thren
    2.06
    POSITIVE LOGITS
     семьи
    3.18
    вання
    2.81
     cercanos
    2.74
    лаго
    2.74
     друга
    2.74
    iduciary
    2.72
    谊
    2.69
    钴
    2.58
     superconduct
    2.56
    jší
    2.52
    Activations Density 0.038%

    No Known Activations