© 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. 2578
    Prev
    Next
    INDEX
    Explanations

    noun phrases with associated adjectives and descriptive verbs

    oai_token-act-pair · gemini-2.0-flash

    indefinite articles and phrases starting with "a" or "an"

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

    is

    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
     насељу
    -0.65
    
    -0.60
     tâ
    -0.57
    timos
    -0.57
    urdu
    -0.55
    ALSO
    -0.54
     enf
    -0.54
    رشف
    -0.54
     Italijanski
    -0.54
    eburger
    -0.53
    POSITIVE LOGITS
     a
    0.97
     an
    0.85
    RenderAtEndOf
    0.69
    XmlAccessType
    0.68
     the
    0.67
    IUrlHelper
    0.66
     seorang
    0.55
     Wikiseite
    0.54
     verantwoorde
    0.54
     einer
    0.52
    Activations Density 2.510%

    No Known Activations