© 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. 16347
    Prev
    Next
    INDEX
    Explanations

    general words often used as articles in descriptive clauses

    oai_token-act-pair · 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
    phe
    -0.41
    I
    -0.40
    and
    -0.36
     necessários
    -0.36
    T
    -0.36
     necesarios
    -0.34
    are
    -0.33
    Blade
    -0.32
    бре
    -0.32
     söyl
    -0.32
    POSITIVE LOGITS
     HasFactory
    1.05
    出版年
    1.03
    TagHelper
    1.02
    Autoritní
    0.95
     Савезне
    0.93
    MigrationBuilder
    0.91
     ExecuteAsync
    0.88
     MainAxisSize
    0.85
    styleType
    0.84
    حوالہ
    0.83
    Activations Density 11.150%

    No Known Activations