© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14838
    Prev
    Next
    INDEX
    Explanations

    the word "rarely", and sometimes highlights "usually", "recently", "both", and "round."

    oai_token-act-pair · gemini-2.0-flash

    rarely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    bootstrapcdn
    -0.67
    rungsseite
    -0.63
    </i>
    -0.63
     européennes
    -0.63
    <bos>
    -0.61
     sanitaires
    -0.59
     économiques
    -0.56
     internacionales
    -0.56
     américains
    -0.55
     europeos
    -0.55
    POSITIVE LOGITS
    BibitemShut
    0.88
    rogels
    0.84
     Jefus
    0.81
    tling
    0.81
     Efq
    0.80
    itespace
    0.80
    orescence
    0.79
     IBRARY
    0.78
     Eſ
    0.78
    moiselle
    0.78
    Activations Density 2.565%

    No Known Activations