© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6185
    Prev
    Next
    INDEX
    Explanations

    code snippets with function calls and variable assignments.

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

    np_token-act-pair-logits · gpt-4o-mini

    code punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    @
    -0.53
    <strong>
    -0.53
    !
    -0.51
    a
    -0.50
    2
    -0.50
    1
    -0.49
    ~
    -0.49
    (
    -0.47
     =
    -0.47
    0
    -0.46
    POSITIVE LOGITS
     oprot
    0.95
    bootstrapcdn
    0.93
    NameInMap
    0.92
     doInBackground
    0.92
     Мексичка
    0.91
     onOptions
    0.90
    <unused23>
    0.89
    <unused28>
    0.89
    <unused14>
    0.89
    <pad>
    0.89
    Activations Density 2.971%

    No Known Activations