© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10780
    Prev
    Next
    INDEX
    Explanations

    words with two consonants in a row

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    出版年
    -0.57
    ted
    -0.54
    ty
    -0.51
    ts
    -0.49
    tic
    -0.49
    sh
    -0.48
     perceived
    -0.46
    t
    -0.45
    tg
    -0.44
    yy
    -0.43
    POSITIVE LOGITS
    UserScript
    0.75
    DHA
    0.69
    ding
    0.69
    dha
    0.69
    dings
    0.68
    DIT
    0.68
    DockStyle
    0.66
    ded
    0.66
    deth
    0.66
    dY
    0.65
    Activations Density 0.644%

    No Known Activations