© 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. 7933
    Prev
    Next
    INDEX
    Explanations

    words concerning patients, reclining chairs, and basketball arrangements

    oai_token-act-pair · gemini-2.0-flash

    phrases related to technical objects or mechanisms

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

    technical descriptions

    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
     greateſt
    -0.60
     defStyleAttr
    -0.50
    yelidikan
    -0.49
    Tazama
    -0.49
     informacija
    -0.47
    ellingham
    -0.47
     Neri
    -0.47
     Geschä
    -0.46
     habet
    -0.45
     artikkelen
    -0.45
    POSITIVE LOGITS
    WriteTagHelper
    0.66
     Drapeau
    0.57
    verwijspagina
    0.56
    Rüyada
    0.53
     Credit
    0.51
    ựng
    0.51
    addContainerGap
    0.50
    VolleyError
    0.50
     slides
    0.50
    BagLayout
    0.49
    Activations Density 6.647%

    No Known Activations