© 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. 1922
    Prev
    Next
    INDEX
    Explanations

    code blocks and related syntax

    oai_token-act-pair · gemini-2.0-flash

    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
     дописавши
    -0.99
     EconPapers
    -0.90
     noDo
    -0.89
    AutoScaleMode
    -0.82
    Personensuche
    -0.79
     Roskov
    -0.73
     endblock
    -0.72
    IntoConstraints
    -0.72
    SourceChecksum
    -0.71
    Personendaten
    -0.69
    POSITIVE LOGITS
    <bos>
    1.20
    __":
    0.64
     ExecuteAsync
    0.61
    '
    0.60
    __':
    0.54
     shouldn
    0.53
    setcounter
    0.52
    mogat
    0.52
    cembre
    0.52
    __':
    0.52
    Activations Density 0.341%

    No Known Activations