© 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. 5956
    Prev
    Next
    INDEX
    Explanations

    phrases related to probability and sampling without replacement

    oai_token-act-pair · gemini-2.0-flash

    formal/technical texts

    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
    rrggbb
    -0.48
     brancas
    -0.46
    contentLoaded
    -0.46
    windowFixed
    -0.45
    loem
    -0.43
    cèse
    -0.41
    DECREF
    -0.41
    Portale
    -0.40
    usepackage
    -0.39
    SBATCH
    -0.39
    POSITIVE LOGITS
    AccessorTable
    0.66
     Majefty
    0.66
    iffion
    0.63
     iſt
    0.62
     In
    0.62
     auffi
    0.62
    ftance
    0.62
    ftant
    0.61
     Perſ
    0.61
     sement
    0.59
    Activations Density 17.413%

    No Known Activations