© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9737
    Prev
    Next
    INDEX
    Explanations

    a combination of bracket characters, the phrase "state of the art", and words related to accomplishment and success.

    oai_token-act-pair · gemini-2.0-flash

    art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    resizingMask
    -0.45
     AttributeSet
    -0.45
     together
    -0.43
     JADX
    -0.41
    opsida
    -0.40
     Attorneys
    -0.40
    ودی
    -0.40
    意味
    -0.40
    prits
    -0.40
    mybatisplus
    -0.40
    POSITIVE LOGITS
    __(/*!
    0.81
    <bos>
    0.76
    theless
    0.69
     незавершена
    0.69
     Offisielt
    0.68
    reactstrap
    0.67
     Numerade
    0.67
    KommentareTeilen
    0.64
    Билгалдахарш
    0.64
    xase
    0.62
    Activations Density 2.505%

    No Known Activations