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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4732
    Prev
    Next
    INDEX
    Explanations

    the prefix "pan-"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of 'pan'

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

    Pan

    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
    psum
    -0.66
     farine
    -0.65
     graphique
    -0.64
     définiti
    -0.63
     juridiques
    -0.63
    anaan
    -0.62
     poussière
    -0.60
     florales
    -0.60
     gagné
    -0.60
     GetComponent
    -0.60
    POSITIVE LOGITS
    tagHelperRunner
    0.49
     pinulongan
    0.47
    Diweddarwch
    0.43
    Beau
    0.43
    ValueStyle
    0.40
     propOrder
    0.40
    Geplaatst
    0.40
     ghost
    0.40
    プレ
    0.40
     kasarigan
    0.40
    Activations Density 0.291%

    No Known Activations