© 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. 5292
    Prev
    Next
    INDEX
    Explanations

    reviewing revising appeal

    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
    े
    2.74
    ه
    2.56
    friend
    2.55
    
    2.54
    giver
    2.45
    மானு
    2.40
    า
    2.38
     entail
    2.38
    
    2.37
    courses
    2.36
    POSITIVE LOGITS
    ిన
    2.68
    ያን
    2.61
    в
    2.58
    стал
    2.56
    $("#
    2.47
     aloud
    2.44
    р
    2.43
     toBe
    2.24
     हड्डी
    2.22
    ImageIcon
    2.21
    Activations Density 0.049%

    No Known Activations