© 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. 5240
    Prev
    Next
    INDEX
    Explanations

    doping, dopamine

    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
    ु
    3.02
     isa
    2.72
    ানের
    2.61
     Escuela
    2.61
    pant
    2.60
     μπορού
    2.55
    ीन
    2.54
     fasten
    2.50
    asing
    2.48
     ouverte
    2.46
    POSITIVE LOGITS
    an
    3.30
    ד
    3.18
    াল
    2.64
    ات
    2.52
    绔
    2.43
    ला
    2.41
    ท์
    2.38
    р
    2.29
    ɖ
    2.27
    ামুটি
    2.27
    Activations Density 0.017%

    No Known Activations