© 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. 5136
    Prev
    Next
    INDEX
    Explanations

    Huaxiaozhu taxi

    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
    न
    3.94
    нің
    2.84
    नं
    2.80
    ম
    2.74
    cities
    2.51
     typu
    2.47
     subparagraph
    2.46
    ר
    2.45
    ब
    2.42
    Nella
    2.39
    POSITIVE LOGITS
    ين
    3.01
    '%
    2.61
    𝒍
    2.45
    u
    2.45
    }$.)
    2.32
     secu
    2.32
    టి
    2.32
     landscaping
    2.32
    ંત
    2.31
     hacia
    2.30
    Activations Density 0.015%

    No Known Activations