© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 14491
    Prev
    Next
    INDEX
    Explanations

    java code using System.out.println

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     Roskov
    -0.65
    \{\\
    -0.65
    :✨
    -0.57
    IVersion
    -0.56
    AutoScaleMode
    -0.55
     GetEnumerator
    -0.54
    িখ
    -0.54
     certes
    -0.52
    MemoryWarning
    -0.52
    RotationOrder
    -0.51
    POSITIVE LOGITS
    <bos>
    1.88
     BoxFit
    0.69
    GenerationType
    0.64
    endphp
    0.63
     AssemblyTitle
    0.55
     actionTypes
    0.53
     IActionResult
    0.53
    #+#
    0.50
    LookAnd
    0.49
    Tags
    0.48
    Activations Density 0.201%

    No Known Activations