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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10451
    Prev
    Next
    INDEX
    Explanations

    technical writing in the field of nanotech, materials science or electronics

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndEndTag
    -0.90
    writeFieldEnd
    -0.80
     &___
    -0.72
    jsonwebtoken
    -0.68
    expandindo
    -0.68
    HasAnnotation
    -0.65
    IContainer
    -0.64
    elemField
    -0.63
    providedIn
    -0.63
    CppMethod
    -0.62
    POSITIVE LOGITS
     state
    0.63
    DoubleQuotes
    0.56
    state
    0.48
    tack
    0.45
     Homem
    0.44
    Aplicaciones
    0.44
     prior
    0.43
     cutting
    0.43
    Homme
    0.42
    <bos>
    0.42
    Activations Density 4.590%

    No Known Activations