© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16067
    Prev
    Next
    INDEX
    Explanations

    words related to clothing, printed publications, and addresses, and specifically the number 1, the letter W, and logos

    oai_token-act-pair · gemini-2.0-flash

    printed labels and information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     calendriers
    -0.44
     Un
    -0.37
     Tro
    -0.35
    colm
    -0.35
    tonsoft
    -0.35
    Offset
    -0.34
    欲
    -0.33
    Un
    -0.33
    RTLI
    -0.33
    CROSSTALK
    -0.33
    POSITIVE LOGITS
    mybatisplus
    0.79
    enumii
    0.70
    AddHtmlAttribute
    0.69
    DoubleQuotes
    0.68
     kasarigan
    0.68
     виправивши
    0.65
    ̈́
    0.65
    aarrggbb
    0.64
    supers
    0.63
    setopt
    0.63
    Activations Density 4.850%

    No Known Activations