© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5294
    Prev
    Next
    INDEX
    Explanations

    your shit, their minds

    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
    प्ताहिक
    1.77
    ત્મક
    1.76
     помнить
    1.73
    於
    1.69
    стал
    1.65
    ಲೆಂ
    1.65
    managedbuild
    1.62
     favourably
    1.61
    લાક
    1.61
    rude
    1.59
    POSITIVE LOGITS
    и
    2.05
    িং
    2.00
    ї
    1.97
    ে
    1.82
    াবেক
    1.78
     tät
    1.77
     következő
    1.76
     што
    1.76
    er
    1.76
    ़
    1.74
    Activations Density 0.048%

    No Known Activations