© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3178
    Prev
    Next
    INDEX
    Explanations

    give it a try

    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
    yon
    0.49
    ுள்ளார்
    0.48
    ು
    0.45
    Người
    0.44
     provincias
    0.44
    可以
    0.44
    ंजनों
    0.44
    ophers
    0.44
    એ
    0.43
    ка
    0.43
    POSITIVE LOGITS
    }$
    0.46
    мум
    0.45
    شنبه
    0.43
     выполнения
    0.43
     blink
    0.42
    }\
    0.40
    achter
    0.40
    }$-
    0.40
    },
    0.39
    رت
    0.38
    Activations Density 0.005%

    No Known Activations