© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4856
    Prev
    Next
    INDEX
    Explanations

    words, especially verbs, related to participation

    oai_token-act-pair · gemini-2.0-flash

    playing sports

    np_max-act-logits · gemini-2.0-flash

    play

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    GeneratedCode
    -0.49
    দ্
    -0.40
    TestingModule
    -0.39
    comy
    -0.39
     ud
    -0.38
    Sw
    -0.38
    ul
    -0.35
    公
    -0.35
    Heter
    -0.35
    бу
    -0.35
    POSITIVE LOGITS
    цездатний
    0.82
    +:+
    0.70
     IndexPath
    0.67
    __(/*!
    0.66
     AssemblyProduct
    0.65
    hatenablog
    0.65
    Портал
    0.65
     BoxDecoration
    0.64
     ErrIntOverflow
    0.64
    راسیون
    0.63
    Activations Density 0.670%

    No Known Activations