© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4939
    Prev
    Next
    INDEX
    Explanations

    adjectives and present tense verbs, especially those ending in -ing or -ed.

    oai_token-act-pair · gemini-2.0-flash

    words related to organization or realization

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

    -isation/-sation words

    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
     Ее
    -1.35
     Еще
    -1.29
    ighborhood
    -1.27
    Еще
    -1.26
     flavors
    -1.22
    ighbor
    -1.20
    ьез
    -1.19
     neighbors
    -1.17
    бенок
    -1.17
     colors
    -1.16
    POSITIVE LOGITS
     şi
    1.77
    Ещё
    1.73
     optimisation
    1.73
     utilisation
    1.64
     realises
    1.63
     realised
    1.63
     organisation
    1.63
     organisations
    1.62
     organisational
    1.61
     optimised
    1.60
    Activations Density 9.167%

    No Known Activations