© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5040
    Prev
    Next
    INDEX
    Explanations

    mentions of talking or conversation

    oai_token-act-pair · gemini-2.0-flash

    talk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Ackerman
    -0.50
     standing
    -0.43
    LayoutConstraint
    -0.43
     joint
    -0.42
     réessayer
    -0.42
     bağlantılar
    -0.41
     sk
    -0.41
    titutional
    -0.41
    deburg
    -0.40
     dispute
    -0.40
    POSITIVE LOGITS
     OFDb
    0.68
    nonatomic
    0.66
    StoryboardSegue
    0.62
    sizeCache
    0.59
    addLast
    0.56
    Salta
    0.56
    клопе
    0.55
    PostMapping
    0.54
     gawas
    0.54
     fathoms
    0.54
    Activations Density 0.512%

    No Known Activations