© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4520
    Prev
    Next
    INDEX
    Explanations

    text with a lot of markup, including unusual characters, quotes and parentheses

    oai_token-act-pair · gemini-2.0-flash

    quote marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     “
    -1.10
     "
    -1.07
     „
    -0.80
     ‘
    -0.71
     ”
    -0.68
    (":");
    -0.66
    ://"
    -0.66
     «
    -0.66
     ":
    -0.65
     "[
    -0.65
    POSITIVE LOGITS
    <bos>
    1.87
     itſelf
    0.91
     myſelf
    0.90
     raiſ
    0.85
     juſt
    0.76
     faſt
    0.74
     uſed
    0.73
    Personendaten
    0.73
     poffible
    0.69
     Monfieur
    0.69
    Activations Density 2.196%

    No Known Activations