© 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. 6178
    Prev
    Next
    INDEX
    Explanations

    over-explaining

    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
    써
    1.50
    )})
    1.44
    credible
    1.41
    выми
    1.41
     plej
    1.39
     suena
    1.39
    вым
    1.39
    ussa
    1.37
    rusty
    1.37
    )])
    1.35
    POSITIVE LOGITS
    다
    1.74
    р
    1.48
    ן
    1.42
    ুয়ার
    1.41
    avic
    1.41
    itr
    1.40
    ណ៍
    1.39
    nour
    1.36
    ست
    1.35
    𝒸
    1.32
    Activations Density 0.112%

    No Known Activations