© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11544
    Prev
    Next
    INDEX
    Explanations

    superlative statements, either of uniqueness or of being the best

    oai_token-act-pair · gemini-2.0-flash

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    AutoScaleMode
    -0.55
     cumplido
    -0.53
     intStringLen
    -0.50
    Hentet
    -0.46
     cumpli
    -0.45
     passée
    -0.43
     cumpri
    -0.43
    <bos>
    -0.42
    minu
    -0.42
    Portály
    -0.42
    POSITIVE LOGITS
     unique
    0.83
     Unique
    0.75
     دیکھیے
    0.72
     unieke
    0.72
     UNIQUE
    0.72
    Unique
    0.70
     uniquely
    0.68
     uniques
    0.68
    unique
    0.68
    VersionUID
    0.65
    Activations Density 0.665%

    No Known Activations