© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5299
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    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
    т
    0.55
    ت
    0.47
    ת
    0.47
    л
    0.46
    al
    0.42
    hearted
    0.40
    یات
    0.35
    ో
    0.35
    그
    0.34
    alen
    0.33
    POSITIVE LOGITS
     inget
    0.55
     encanta
    0.48
     wasps
    0.47
     plexus
    0.46
     vei
    0.45
     sigue
    0.45
     voici
    0.45
     vieja
    0.44
     ziemlich
    0.44
     dä
    0.44
    Activations Density 0.922%

    No Known Activations