© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5168
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

    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
    м
    3.58
    क
    3.39
    ين
    3.37
     immobilier
    2.96
    ियां
    2.93
    ът
    2.81
    te
    2.80
    お
    2.73
    लिये
    2.70
    р
    2.70
    POSITIVE LOGITS
    eské
    3.15
    ea
    3.04
    "%(
    2.94
    aS
    2.90
    ीय
    2.90
    hw
    2.80
    eee
    2.77
    '$.
    2.71
     councillor
    2.70
    setImageResource
    2.69
    Activations Density 0.005%

    No Known Activations