© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13333
    Prev
    Next
    INDEX
    Explanations

    multiple seemingly unrelated short phrases that often include time-related words or verbs.

    oai_token-act-pair · gemini-2.0-flash

    over

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    expandindo
    -0.87
     متعلقه
    -0.67
    .*")]
    -0.65
    
    -0.65
    esModule
    -0.63
    ViewFeatures
    -0.60
    thalene
    -0.60
     GenerationType
    -0.59
    \{\\
    -0.58
    AccessorTable
    -0.57
    POSITIVE LOGITS
     over
    2.52
    over
    1.92
     Over
    1.89
    Over
    1.84
     OVER
    1.72
     över
    1.63
    OVER
    1.46
     über
    1.45
    オーバー
    1.30
    overs
    1.16
    Activations Density 1.856%

    No Known Activations