© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4904
    Prev
    Next
    INDEX
    Explanations

    adverbs, prepositions, and conjunctions that change the tense or outcome of an action.

    oai_token-act-pair · gemini-2.0-flash

    package management and programming contexts

    np_token-act-pair-logits · gpt-4o-mini
    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
     again
    -1.52
     erneut
    -1.40
    Again
    -1.39
    again
    -1.39
     renewed
    -1.36
    再次
    -1.36
     continued
    -1.34
     Again
    -1.32
     continuation
    -1.28
     tekrar
    -1.28
    POSITIVE LOGITS
    #
    0.90
    gonic
    0.75
     Савезне
    0.69
    MessageOf
    0.67
     ExecuteAsync
    0.67
    SourceChecksum
    0.66
    msgTypes
    0.65
     Biôgrafia
    0.61
    UrlResolution
    0.60
    AndEndTag
    0.59
    Activations Density 0.688%

    No Known Activations