© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "being" and words that come right before or after it

    oai_token-act-pair · gemini-2.0-flash

    actions in progress

    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
     gånger
    -0.69
     Fälle
    -0.69
     divent
    -0.69
     esetben
    -0.68
     rimanere
    -0.68
     tider
    -0.65
     essendo
    -0.64
     preocupes
    -0.63
     étant
    -0.62
     mať
    -0.62
    POSITIVE LOGITS
    
    0.71
    хьтан
    0.55
    __':
    0.55
     дописавши
    0.54
    nemone
    0.54
    textAppearance
    0.54
    >//
    0.54
    toHaveBeenCalled
    0.54
    providedIn
    0.54
    WithIOException
    0.52
    Activations Density 1.707%

    No Known Activations