Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3826
    Prev
    Next
    INDEX
    Explanations

    environment and sustainability

    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
    }$
    0.57
    iy
    0.55
    ToMany
    0.48
    stays
    0.47
    watering
    0.45
    een
    0.45
     ביותר
    0.43
    [],
    0.43
    iyati
    0.43
     pues
    0.43
    POSITIVE LOGITS
     lagoons
    0.51
     রহমান
    0.50
     শন
    0.49
     организм
    0.49
     passing
    0.49
     Nutzen
    0.48
     policing
    0.48
     neodymium
    0.48
     créé
    0.47
     carbono
    0.47
    Activations Density 0.167%

    No Known Activations