© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5397
    Prev
    Next
    INDEX
    Explanations

    various words that are often close to personal names, as well as "as saying" and some other common words

    oai_token-act-pair · gemini-2.0-flash

    say

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     professionale
    -0.54
    Numerology
    -0.51
     professionali
    -0.48
    Datuak
    -0.48
    GeneratedCode
    -0.47
     interessieren
    -0.43
     према
    -0.42
     uska
    -0.41
     minori
    -0.40
     blom
    -0.40
    POSITIVE LOGITS
     saying
    1.05
     stating
    0.96
     sayin
    0.94
     told
    0.94
     tells
    0.91
     mengatakan
    0.91
     berkata
    0.89
     say
    0.87
     said
    0.87
     telling
    0.85
    Activations Density 3.821%

    No Known Activations