© 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. 16159
    Prev
    Next
    INDEX
    Explanations

    adjectives that use "high-" to indicate quality, rank, or timescale

    oai_token-act-pair · gemini-2.0-flash

    dash

    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
    ########.
    -0.84
    MENAFN
    -0.77
    CppMethod
    -0.75
    Geplaatst
    -0.73
    SpringBootTest
    -0.72
    исленность
    -0.72
    makeConstraints
    -0.70
    encodeWith
    -0.69
     itſelf
    -0.69
    <bos>
    -0.69
    POSITIVE LOGITS
    .
    0.59
    ed
    0.44
    ten
    0.38
    d
    0.36
    '
    0.35
     fallu
    0.35
    cal
    0.34
     próprias
    0.33
     skala
    0.33
    ter
    0.33
    Activations Density 1.861%

    No Known Activations