© 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. 3551
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    ங்கிணை
    1.24
     atthe
    1.07
     lounges
    1.06
     sg
    1.04
    ened
    1.00
    เจน
    0.99
    푐
    0.97
     centrifug
    0.96
     tandis
    0.96
    า
    0.95
    POSITIVE LOGITS
    huis
    1.03
    ER
    0.90
    er
    0.89
    யில்
    0.89
    tól
    0.88
    ر
    0.86
    kla
    0.84
    ર
    0.82
    и
    0.79
    自分
    0.78
    Activations Density 0.012%

    No Known Activations