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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3395
    Prev
    Next
    INDEX
    Explanations

    the words "but," "so," "all," and related grammatical words like "the".

    oai_token-act-pair · gemini-2.0-flash

    pronouns and function keywords

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

    Expressing opinions or thoughts

    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
     ་་
    -0.71
     betweenstory
    -0.71
    */)
    -0.69
    >");
    -0.68
    ')")
    -0.65
    */;
    -0.64
    ()?;
    -0.64
     متعلقه
    -0.64
    )*/
    -0.63
     ―――――
    -0.62
    POSITIVE LOGITS
     he
    0.65
     they
    0.59
    addPreferredGap
    0.57
     this
    0.56
    strcmp
    0.54
     viewDidLoad
    0.54
    MemoryWarning
    0.52
     we
    0.52
     (
    0.51
    věr
    0.51
    Activations Density 1.538%

    No Known Activations