© 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. 10219
    Prev
    Next
    INDEX
    Explanations

    contentions and disagreements

    oai_token-act-pair · gemini-2.0-flash

    terms related to separation or distance

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

    separation or distance

    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
    usione
    -0.48
    complexContent
    -0.46
     hjælpe
    -0.43
    cinogen
    -0.41
    ercizio
    -0.41
    therosclerosis
    -0.40
    voj
    -0.39
    zam
    -0.39
    Décès
    -0.37
    harusnya
    -0.37
    POSITIVE LOGITS
     afstand
    0.81
     distance
    0.80
     estrange
    0.77
     Distances
    0.76
     distances
    0.76
     coolness
    0.75
     rupture
    0.73
     насељу
    0.73
     coldness
    0.73
     rift
    0.71
    Activations Density 1.803%

    No Known Activations