© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3219
    Prev
    Next
    INDEX
    Explanations

    free plan or tier

    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_5_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
    י
    1.51
    رب
    1.32
     corrections
    1.31
    aklar
    1.26
    साइटी
    1.26
    部
    1.25
    ஜ்மஹால்
    1.25
    ی
    1.24
    إنجليزية
    1.23
    িল্লি
    1.21
    POSITIVE LOGITS
    ce
    1.49
    𝒸
    1.28
    bies
    1.27
    те
    1.25
    р
    1.25
    CE
    1.22
    Hasta
    1.20
    ва
    1.18
    ন
    1.17
    ruption
    1.17
    Activations Density 0.061%

    No Known Activations