© 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. 3487
    Prev
    Next
    INDEX
    Explanations

    bracketed figure and table references

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     itſelf
    -0.84
     Theſe
    -0.81
     الحره
    -0.73
     myſelf
    -0.73
     themſelves
    -0.72
     caufe
    -0.70
     propOrder
    -0.70
     becauſe
    -0.69
     pinch
    -0.69
    Geplaatst
    -0.69
    POSITIVE LOGITS
    </strong>
    0.55
     opérés
    0.45
     ver
    0.43
    findpost
    0.43
     NgModule
    0.42
     argparse
    0.41
    Javadoc
    0.40
     demografica
    0.40
    '}
    0.39
    ubblica
    0.39
    Activations Density 24.553%

    No Known Activations