© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13250
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases, especially temporal ones like built-in

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -1.35
    -
    -1.28
    ’
    -0.67
    '
    -0.65
    _
    -0.63
    (
    -0.61
    =
    -0.56
     
    -0.52
     -
    -0.51
    </b>
    -0.49
    POSITIVE LOGITS
     myſelf
    0.95
     Majefty
    0.83
     leaſt
    0.81
    wiſe
    0.81
    ſelf
    0.79
     Houſe
    0.79
     étanche
    0.78
     dévelo
    0.78
     purpoſe
    0.77
    تقاوى
    0.77
    Activations Density 0.988%

    No Known Activations