© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11184
    Prev
    Next
    INDEX
    Explanations

    underscores separating words

    oai_token-act-pair · gemini-2.0-flash

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    '
    -1.30
    ’
    -0.84
    H
    -0.83
    3
    -0.80
    i
    -0.80
    D
    -0.78
    ,
    -0.77
    f
    -0.77
    C
    -0.76
    n
    -0.76
    POSITIVE LOGITS
    utterstock
    1.13
    ratulations
    1.09
    jectures
    1.05
    VIAF
    1.05
    haviors
    1.02
    iffance
    1.01
    uests
    1.00
    tershire
    1.00
    iffion
    0.98
    drawal
    0.96
    Activations Density 1.138%

    No Known Activations