© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5567
    Prev
    Next
    INDEX
    Explanations

    code imports and/or annotations in Python

    oai_token-act-pair · gemini-2.0-flash

    words related to importing libraries or modules

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

    Python code imports

    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
    fjspx
    -0.81
    hyrchwyd
    -0.63
    vernote
    -0.58
    Referencoj
    -0.57
    AddTagHelper
    -0.57
     للمعارف
    -0.57
    Filmografie
    -0.57
    ναι
    -0.54
    ECAUSE
    -0.54
    ourtney
    -0.54
    POSITIVE LOGITS
    from
    0.71
     from
    0.59
     tartalomajánló
    0.58
    +#+#
    0.58
     Bourgoin
    0.56
     cogn
    0.53
    庁
    0.52
    хіво
    0.50
     ['./
    0.50
    From
    0.49
    Activations Density 1.601%

    No Known Activations