© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6400
    Prev
    Next
    INDEX
    Explanations

    javascript code fragments

    oai_token-act-pair · gemini-2.0-flash

    =

    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
    Console
    -0.54
     edelstahl
    -0.52
     console
    -0.51
     window
    -0.50
    </h1>
    -0.49
    ĩnh
    -0.49
    imov
    -0.48
     number
    -0.48
     سكانية
    -0.47
     optique
    -0.47
    POSITIVE LOGITS
     '.';
    0.86
     '-';
    0.84
     $('<
    0.77
     '-':
    0.68
     '/';
    0.67
     '/':
    0.66
    TypedDataSet
    0.66
     /\.(
    0.66
     '?'
    0.65
     '*':
    0.65
    Activations Density 3.600%

    No Known Activations