© 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. 3887
    Prev
    Next
    INDEX
    Explanations

    code snippets that can be in a variety of computer languages

    oai_token-act-pair · gemini-2.0-flash

    Game programming code

    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
    <bos>
    -0.65
     resourceCulture
    -0.60
    ↵↵
    -0.47
    esque
    -0.44
    ","
    -0.43
    }}}{
    -0.43
    -
    -0.42
    jspb
    -0.42
    js
    -0.41
    点
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    0.85
    VersionUID
    0.82
    KURZBESCHREIBUNG
    0.74
    ⓧ
    0.73
     الحره
    0.73
    HomeAsUpEnabled
    0.69
    ivably
    0.68
     ſame
    0.68
    قایناقلار
    0.67
    ]")]
    0.65
    Activations Density 14.709%

    No Known Activations