© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 376
    Prev
    Next
    INDEX
    Explanations

    strings of math symbols, numbers, and punctuation.

    oai_token-act-pair · gemini-2.0-flash

    say [underscore]

    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
     $\$
    -2.47
    \\
    -2.16
    .\\
    -2.14
     ${
    -2.13
     \&
    -2.08
    \_
    -2.06
     \$
    -2.02
     \#
    -1.98
    \&
    -1.98
     $\
    -1.95
    POSITIVE LOGITS
    ”—
    0.46
    —”
    0.45
    Ự
    0.44
     utafiti
    0.43
    "—
    0.42
    +#+
    0.40
    SaveChangesAsync
    0.40
     -->>
    0.39
    --]
    0.38
    ‘’
    0.38
    Activations Density 10.344%

    No Known Activations