© 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. 374
    Prev
    Next
    INDEX
    Explanations

    numbers within code, especially those found in file readouts or logs

    oai_token-act-pair · 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
    ,
    -2.55
    ，
    -1.22
    ,
    -1.22
    ،
    -1.17
    (),
    -1.12
    StoryboardSegue
    -1.09
    ,<
    -1.02
    _,
    -1.02
    、
    -0.98
     ,
    -0.96
    POSITIVE LOGITS
    ждён
    0.35
    mässig
    0.35
    יש
    0.31
    LETON
    0.31
    TagHelper
    0.30
    melidir
    0.30
    ẾT
    0.29
    ‘’
    0.29
    liegt
    0.28
    lustre
    0.28
    Activations Density 1.020%

    No Known Activations