© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15071
    Prev
    Next
    INDEX
    Explanations

    time durations

    oai_token-act-pair · gemini-2.0-flash

    Time durations

    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
    IBOutlet
    -0.59
     ten
    -0.55
    JvmStatic
    -0.53
     nine
    -0.52
     eleven
    -0.52
    
    -0.51
    HttpDelete
    -0.51
    CPtr
    -0.50
    WriteBarrier
    -0.50
    CJK
    -0.49
    POSITIVE LOGITS
    +#+
    0.69
    InjectAttribute
    0.61
    ✨:
    0.57
     PLW
    0.50
    liato
    0.50
     jelly
    0.46
    tablissements
    0.45
    dicionado
    0.44
     fertilized
    0.44
     wash
    0.44
    Activations Density 1.864%

    No Known Activations