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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8590
    Prev
    Next
    INDEX
    Explanations

    am / are + adjective / noun

    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
    𝐭
    3.09
    ه
    3.02
    años
    2.97
    𝐮
    2.72
    𝐡
    2.67
    𝐫
    2.60
    𝐝
    2.59
    нні
    2.59
    สุด
    2.59
     Been
    2.57
    POSITIVE LOGITS
    на
    3.43
    ка
    3.41
    ु
    3.31
    l
    2.87
    ity
    2.85
    lly
    2.61
    我认为
    2.59
    ש
    2.49
    هم
    2.42
    碼
    2.39
    Activations Density 0.162%

    No Known Activations