© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3481
    Prev
    Next
    INDEX
    Explanations

    python code structure

    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
    e
    1.06
    aaa
    0.96
    е
    0.86
    aaaa
    0.84
    Ϟ
    0.84
    aa
    0.84
     lust
    0.82
    рами
    0.82
    </
    0.82
    _{
    0.82
    POSITIVE LOGITS
    ibbean
    1.09
     equivariant
    1.06
     الواحده
    1.00
    ೀವ
    0.99
    porter
    0.99
    نٹ
    0.98
     łącz
    0.96
    ालय
    0.95
    検証
    0.94
    ぺ
    0.94
    Activations Density 0.152%

    No Known Activations