© 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. 5612
    Prev
    Next
    INDEX
    Explanations

    must, need, always

    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
    𝗆
    1.44
    ванням
    1.32
    ingly
    1.30
    ocentric
    1.24
    燹
    1.23
    \/}
    1.23
    }}
    1.20
    𝗌
    1.16
    কায়
    1.15
     सेक्टर
    1.14
    POSITIVE LOGITS
    م
    1.49
    talet
    1.46
    től
    1.32
    ouncing
    1.30
     Перейти
    1.29
    પણે
    1.29
    ารณา
    1.28
    existent
    1.27
     strane
    1.25
    ند
    1.24
    Activations Density 0.046%

    No Known Activations