© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13589
    Prev
    Next
    INDEX
    Explanations

    female first names, sometimes paired with associated words

    oai_token-act-pair · gemini-2.0-flash

    people's names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     rank
    -0.45
    <eos>
    -0.44
    nik
    -0.42
    rank
    -0.42
    Initialize
    -0.41
    اصر
    -0.40
     ha
    -0.39
    膳
    -0.38
    ri
    -0.38
    eden
    -0.36
    POSITIVE LOGITS
     myſelf
    1.01
     Theſe
    0.92
     himſelf
    0.92
     poffible
    0.91
    parsedMessage
    0.88
     raiſ
    0.87
    styleType
    0.87
     themſelves
    0.87
     kaarangay
    0.87
    FTFY
    0.86
    Activations Density 2.205%

    No Known Activations