© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3053
    Prev
    Next
    INDEX
    Explanations

    .com, .org, .io, log

    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_5_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
    manifolds
    0.05
    }}_{
    0.05
    ținut
    0.05
     ditches
    0.05
    Ș
    0.05
     evidenced
    0.05
    nrows
    0.05
    #![
    0.04
    ु
    0.04
    }}_{\
    0.04
    POSITIVE LOGITS
    пъл
    0.05
     nerveux
    0.04
    𝐬
    0.04
    嵌套
    0.04
    𝖘
    0.04
    物に
    0.04
    物
    0.04
     наста
    0.04
    ലൈ
    0.04
    𝐢
    0.04
    Activations Density 0.000%

    No Known Activations