© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13013
    Prev
    Next
    INDEX
    Explanations

    instances of things emerging or originating from something

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     free
    -0.62
     
    -0.50
     d
    -0.47
     complete
    -0.47
     Free
    -0.45
    <u>
    -0.45
    UI
    -0.44
     para
    -0.42
     per
    -0.41
    free
    -0.40
    POSITIVE LOGITS
    BufferException
    1.18
    SourceChecksum
    1.18
    AsUp
    1.09
     pinulongan
    1.08
    LookAnd
    1.05
     الرياضيه
    1.02
     defaultstate
    0.98
    ScopeManager
    0.97
     Мексичка
    0.96
     المعيارى
    0.95
    Activations Density 2.243%

    No Known Activations