© 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. 3721
    Prev
    Next
    INDEX
    Explanations

    words that represent improving something

    oai_token-act-pair · gemini-2.0-flash

    terms related to improvement and enhancement

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

    improve/increase

    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
     createContext
    -0.44
     kanssa
    -0.44
     tää
    -0.41
     él
    -0.41
     trống
    -0.41
     cambiamento
    -0.41
     μεγ
    -0.40
     οποία
    -0.40
    zzar
    -0.40
     affrontare
    -0.39
    POSITIVE LOGITS
     the
    0.86
    Portale
    0.75
    ISupport
    0.64
    ViewFeatures
    0.61
     Савезне
    0.60
    +:+
    0.59
     portability
    0.59
    ///</
    0.58
    #+#
    0.57
    ":[{
    0.57
    Activations Density 3.767%

    No Known Activations