© 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. 12201
    Prev
    Next
    INDEX
    Explanations

    parts of a research paper describing the methods and results

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating research or findings

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

    We

    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
    WithMany
    -0.63
    /**
    -0.50
    BeginContext
    -0.48
     BoxFit
    -0.48
     knex
    -0.47
    ngiliz
    -0.46
    Hochspringen
    -0.46
    اتها
    -0.45
    zda
    -0.44
     وتسجيلات
    -0.44
    POSITIVE LOGITS
     collected
    0.70
     showed
    0.66
    UserScript
    0.65
     use
    0.64
     took
    0.61
     actionMode
    0.60
     demonstrated
    0.60
    цездатний
    0.60
    ِّف
    0.59
     sampled
    0.59
    Activations Density 4.800%

    No Known Activations