© 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. 5809
    Prev
    Next
    INDEX
    Explanations

    Ilford HP5, Brentford, Branford

    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
    ি
    2.55
     века
    2.50
    ildi
    2.41
    ול
    2.39
     tanto
    2.34
    ू
    2.34
    שות
    2.33
     stelle
    2.31
    editText
    2.30
    ளில்
    2.30
    POSITIVE LOGITS
    त
    3.19
    眉头
    2.54
     затем
    2.51
    علم
    2.43
    d
    2.41
    στά
    2.39
    л
    2.36
    不再
    2.32
    з
    2.31
    an
    2.31
    Activations Density 0.000%

    No Known Activations