© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13008
    Prev
    Next
    INDEX
    Explanations

    lines of code

    oai_token-act-pair · gemini-2.0-flash

    public

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AsUp
    -0.96
    PreferredItem
    -0.95
     Efq
    -0.94
     Italijanski
    -0.90
     propOrder
    -0.87
     fieldNum
    -0.84
     betweenstory
    -0.84
    يكب
    -0.82
     فريبيس
    -0.82
    ThroughAttribute
    -0.81
    POSITIVE LOGITS
     cre
    0.50
     class
    0.47
     _
    0.47
     memb
    0.45
     
    0.44
    fut
    0.44
     .
    0.43
    lates
    0.42
    hoho
    0.42
     id
    0.41
    Activations Density 0.435%

    No Known Activations