© 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. 12357
    Prev
    Next
    INDEX
    Explanations

    descriptions of events happening

    oai_token-act-pair · gemini-2.0-flash

    words indicating movement or transition

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

    onto/into

    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
     تضيفلها
    -0.84
     EconPapers
    -0.72
     drin
    -0.68
    Aholisi
    -0.58
    ContentAlignment
    -0.57
     autorytatywna
    -0.56
    Demografía
    -0.55
    EndGlobal
    -0.55
    DoubleQuotes
    -0.54
    ]._
    -0.53
    POSITIVE LOGITS
     onto
    1.94
     into
    1.58
    into
    1.34
    onto
    1.24
     INTO
    1.23
    Into
    1.20
     Into
    1.16
    INTO
    1.13
     Ont
    1.11
    Ont
    1.09
    Activations Density 1.757%

    No Known Activations