© 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. 6562
    Prev
    Next
    INDEX
    Explanations

    future and conditional tense verbs.

    oai_token-act-pair · gemini-2.0-flash

    future tense

    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
     المعيارى
    -0.53
    Candidate
    -0.50
     empres
    -0.49
     pygame
    -0.49
     wept
    -0.49
     jurí
    -0.49
    BeginContext
    -0.48
    ện
    -0.48
     debía
    -0.48
     Unido
    -0.48
    POSITIVE LOGITS
     विश्वसनीयता
    0.69
    CppMethod
    0.68
    featureID
    0.66
    GEBURTSDATUM
    0.65
     initComponents
    0.59
     help
    0.58
     تضيفلها
    0.56
    RuleContext
    0.54
     be
    0.53
    ScopeManager
    0.53
    Activations Density 0.744%

    No Known Activations