© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11160
    Prev
    Next
    INDEX
    Explanations

    words related to creating art, giving input, or drinking

    oai_token-act-pair · gemini-2.0-flash

    stroke sip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ModelAdmin
    -0.73
    complexType
    -0.67
     &'
    -0.57
     GenerationType
    -0.55
    yses
    -0.54
    Citations
    -0.54
    columnNumber
    -0.54
    Sprintf
    -0.54
    simpleType
    -0.52
     restTemplate
    -0.52
    POSITIVE LOGITS
     Roskov
    0.67
    脚注の使い方
    0.57
     متعلقه
    0.52
     NUKAT
    0.49
    yttä
    0.48
    ArrowToggle
    0.47
     necessariamente
    0.45
    Geplaatst
    0.45
     necesariamente
    0.45
    帖最后由
    0.44
    Activations Density 2.380%

    No Known Activations