© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3508
    Prev
    Next
    INDEX
    Explanations

    punctuation at the end of sentences or clauses, sometimes in the context of a philosophical question.

    oai_token-act-pair · gemini-2.0-flash

    specific names or titles

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

    nonsensical text

    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
    KommentareTeilen
    -0.55
     L
    -0.53
     es
    -0.51
    /';
    -0.49
    /";
    -0.48
    /");
    -0.47
     l
    -0.46
     (
    -0.45
     M
    -0.44
     di
    -0.43
    POSITIVE LOGITS
     Shakspeare
    0.88
    RenderAtEndOf
    0.81
     Offisielt
    0.81
     AssemblyTitle
    0.80
    ISupport
    0.79
     Superhost
    0.75
    ConstraintMaker
    0.75
     للمعارف
    0.72
     AssemblyProduct
    0.70
     Cæsar
    0.70
    Activations Density 0.633%

    No Known Activations