© 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. 4203
    Prev
    Next
    INDEX
    Explanations

    words followed by prepositions and articles, especially in the context of awards, meetings, and file paths

    oai_token-act-pair · gemini-2.0-flash

    data processing

    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
     الحره
    -0.80
    +:+
    -0.63
    vádz
    -0.62
    __':
    -0.57
    __':
    -0.54
    ArgsConstructor
    -0.52
    Geplaatst
    -0.51
     offerte
    -0.50
    >[]
    -0.49
    erover
    -0.49
    POSITIVE LOGITS
    InSection
    0.54
     createContext
    0.52
    writeFieldEnd
    0.51
    ronpa
    0.51
     CreateTagHelper
    0.50
    StoryboardSegue
    0.50
    opsida
    0.50
    ActionPerformed
    0.48
     GetComponent
    0.48
    AddHtmlAttribute
    0.47
    Activations Density 1.929%

    No Known Activations