© 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. 5983
    Prev
    Next
    INDEX
    Explanations

    move on or forward

    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
    𝑎
    2.64
     purview
    2.63
    𝑥
    2.62
    𝑦
    2.57
    𝑏
    2.55
    পক্ষ
    2.55
    +}$
    2.47
    ViewGroup
    2.42
    Seriously
    2.41
     nuisance
    2.39
    POSITIVE LOGITS
    𝓵
    2.67
    و
    2.65
    м
    2.60
    ve
    2.55
    er
    2.54
    ye
    2.49
    comers
    2.48
     mundur
    2.45
    ى
    2.45
    शील
    2.43
    Activations Density 0.062%

    No Known Activations