© 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. 10172
    Prev
    Next
    INDEX
    Explanations

    JavaScript code syntax and structures

    oai_token-act-pair · gemini-2.0-flash

    words with unusual spelling or archaic forms

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

    (

    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
     (
    -0.79
     
    -0.59
     I
    -0.59
     di
    -0.57
     R
    -0.57
    <bos>
    -0.57
     of
    -0.55
     me
    -0.53
     N
    -0.51
     an
    -0.51
    POSITIVE LOGITS
     Monfieur
    1.24
     myſelf
    1.21
     Jefus
    1.20
     ſeveral
    1.15
     itſelf
    1.12
     ſche
    1.08
     purpoſe
    1.07
     greateſt
    1.07
     Reſ
    1.05
     Efq
    1.05
    Activations Density 1.611%

    No Known Activations