© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12965
    Prev
    Next
    INDEX
    Explanations

    code-related tokens like error messages, variable types, and functions involving RESTful APIs

    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
     TextAppearance
    -0.59
     doInBackground
    -0.57
    DoubleQuotes
    -0.57
     dieß
    -0.56
    ponenten
    -0.56
    קישורים
    -0.56
     raiſ
    -0.56
     purpoſe
    -0.56
     noDo
    -0.55
     chofe
    -0.53
    POSITIVE LOGITS
    
    0.76
    xDB
    0.58
    emlrt
    0.55
     Mer
    0.47
    ⓧ
    0.47
    avari
    0.46
    mockMvc
    0.46
    esercito
    0.45
    InputChange
    0.45
     diarias
    0.45
    Activations Density 1.726%

    No Known Activations