© 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. 3622
    Prev
    Next
    INDEX
    Explanations

    may or may not

    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
    কে
    0.40
    Blend
    0.37
    COMMIT
    0.34
    ،
    0.33
    };
    0.33
    },
    0.33
    Xcode
    0.33
    Optimization
    0.32
    |
    0.32
    Ви
    0.32
    POSITIVE LOGITS
    ቆዳ
    0.40
     goodness
    0.39
    ুর
    0.38
    ﻰ
    0.38
     Meanwhile
    0.37
    ﴿
    0.37
    ھی
    0.37
     miraculously
    0.37
     fear
    0.36
     totality
    0.36
    Activations Density 0.139%

    No Known Activations