© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3346
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns paired with forms of the verb "to be" or "to have" in French fragments.

    oai_token-act-pair · gemini-2.0-flash

    online chat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    sidemargin
    -0.62
    OGND
    -0.52
     numerus
    -0.45
     inflater
    -0.40
    ècie
    -0.39
    withIdentifier
    -0.38
    WithTag
    -0.38
     vær
    -0.37
    clusal
    -0.36
    Brainz
    -0.36
    POSITIVE LOGITS
     متعلقه
    0.97
     itſelf
    0.91
     juſ
    0.86
     purpoſe
    0.85
     ſtate
    0.85
     pleaſure
    0.85
     uſed
    0.81
     houſe
    0.80
     reaſon
    0.80
     myſelf
    0.78
    Activations Density 2.945%

    No Known Activations