© 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. 6025
    Prev
    Next
    INDEX
    Explanations

    knife

    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
    ر
    3.03
     attendant
    2.95
    𝐟
    2.59
     supposed
    2.51
    tt
    2.46
    ру
    2.34
    it
    2.32
    منى
    2.31
    stätten
    2.28
     strata
    2.27
    POSITIVE LOGITS
    я
    2.39
     אחד
    2.38
    ు
    2.29
     covenant
    2.20
    holy
    2.20
    ை
    2.15
    otle
    2.13
     burglar
    2.11
     resuelve
    2.11
    ими
    2.09
    Activations Density 0.006%

    No Known Activations