© 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. 3960
    Prev
    Next
    INDEX
    Explanations

    the word "age" or the prefixes "up", "ins", "ni" in varied contexts.

    oai_token-act-pair · gemini-2.0-flash

    age and pronouns

    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
    ſelves
    -1.11
     myſelf
    -1.05
     ſever
    -1.04
     purpoſe
    -1.01
     pleaſure
    -1.00
     ſche
    -0.98
    ſelf
    -0.98
     themſelves
    -0.95
     Anſ
    -0.95
     iſt
    -0.94
    POSITIVE LOGITS
     d
    0.86
     h
    0.84
     v
    0.80
     w
    0.79
     g
    0.77
     st
    0.71
     re
    0.69
     am
    0.69
     f
    0.68
     b
    0.68
    Activations Density 2.226%

    No Known Activations