© 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. 5658
    Prev
    Next
    INDEX
    Explanations

    first and second person pronouns, along with related auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    general text

    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
     Majefty
    -0.79
     Monfieur
    -0.79
    Czytaj
    -0.78
     Jefus
    -0.77
     neceffary
    -0.76
     themſelves
    -0.73
    }`).
    -0.71
     Efq
    -0.71
     poffible
    -0.71
     neceff
    -0.70
    POSITIVE LOGITS
     AspNetCore
    0.45
    complexContent
    0.42
     Infórmanos
    0.41
    MergeFrom
    0.39
     NUKAT
    0.38
    queryInterface
    0.38
     Outer
    0.36
    LookAnd
    0.35
    BASELINE
    0.35
    CppMethod
    0.35
    Activations Density 2.957%

    No Known Activations