© 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. 13819
    Prev
    Next
    INDEX
    Explanations

    words and phrases about quantity, progress, magnitude and importance

    oai_token-act-pair · gemini-2.0-flash

    words with uncommon letter patterns

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

    positive qualities or impacts

    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
     a
    -1.00
     an
    -0.90
     very
    -0.73
     quite
    -0.71
     muito
    -0.67
     molto
    -0.63
     muy
    -0.61
     zeer
    -0.61
     mocno
    -0.60
    very
    -0.59
    POSITIVE LOGITS
     pleaſure
    0.87
     Majefty
    0.72
     houſe
    0.70
     ſame
    0.69
     exposure
    0.69
     levels
    0.68
     purpoſe
    0.65
     amounts
    0.65
     flexibility
    0.64
     juſ
    0.64
    Activations Density 3.835%

    No Known Activations