© 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. 6475
    Prev
    Next
    INDEX
    Explanations

    words related to facts or findings.

    oai_token-act-pair · gemini-2.0-flash

    the word 'as' and translations

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

    say "as"

    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
    Vidite
    -0.59
    Jîn
    -0.56
    StreetMap
    -0.52
    曖昧さ回避
    -0.51
     الحره
    -0.50
     كومونز
    -0.50
     onOptions
    -0.50
    TableHead
    -0.49
    さつ
    -0.49
    Enllaces
    -0.49
    POSITIVE LOGITS
     as
    0.99
    Jeografia
    0.69
    sebagai
    0.63
    as
    0.61
     ως
    0.61
    作为
    0.59
     sebagai
    0.59
     як
    0.57
     titolata
    0.57
     spagno
    0.56
    Activations Density 23.430%

    No Known Activations