© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5555
    Prev
    Next
    INDEX
    Explanations

    German words and sentence structure

    oai_token-act-pair · gemini-2.0-flash

    programming terms or keywords

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ]<=
    -0.54
    SPJ
    -0.48
    Bindable
    -0.47
     entirely
    -0.47
     незавершена
    -0.46
    InnerText
    -0.46
    ///<
    -0.45
    ]>=
    -0.45
     елның
    -0.45
     dizem
    -0.44
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.64
     ujednoznacz
    0.60
    neem
    0.59
     Walkover
    0.58
    habit
    0.56
    forName
    0.56
    ofag
    0.56
    quién
    0.56
    iseta
    0.55
    parsedMessage
    0.55
    Activations Density 0.287%

    No Known Activations