© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9013
    Prev
    Next
    INDEX
    Explanations

    code snippets or references to coding

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeatletter
    -0.61
     sereia
    -0.61
     plegable
    -0.59
     küpe
    -0.59
     esimer
    -0.57
     dourada
    -0.56
    Filmografie
    -0.56
    uxta
    -0.56
    sự
    -0.56
     esigen
    -0.54
    POSITIVE LOGITS
     חיצוניים
    0.75
     saites
    0.64
     الرياضيه
    0.62
     Réponses
    0.59
    ])))
    0.59
    ]))
    0.57
    ніципа
    0.57
    ="")
    0.56
    ）。
    0.56
    ”)
    0.56
    Activations Density 44.416%

    No Known Activations