© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4455
    Prev
    Next
    INDEX
    Explanations

    code snippets with words like 'current', 'error', 'thread', 'BOOL', 'String', 'new', 'detect', which might indicate it's looking for attributes/variables/properties within code.

    oai_token-act-pair · gemini-2.0-flash

    current or new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    lė
    -0.44
     state
    -0.41
    +#+
    -0.40
    ViewImports
    -0.40
    stasia
    -0.38
    tigungs
    -0.38
    nictwa
    -0.38
    __).
    -0.37
     bear
    -0.37
     PTT
    -0.35
    POSITIVE LOGITS
    GOTREF
    0.81
    хьтан
    0.79
     initComponents
    0.73
     समीक्षक
    0.73
    AnchorStyles
    0.73
    GEBURTSDATUM
    0.71
    setVerticalGroup
    0.71
    Geplaatst
    0.71
    IUrlHelper
    0.71
     nakalista
    0.71
    Activations Density 55.303%

    No Known Activations