© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14441
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "part" and words like "level", "scale", "class" and "ongoing."

    oai_token-act-pair · gemini-2.0-flash

    part

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    e
    -0.67
    ew
    -0.53
    ex
    -0.52
    ed
    -0.51
    em
    -0.49
    eX
    -0.48
    Geplaatst
    -0.47
    vacy
    -0.47
    mH
    -0.47
    eid
    -0.47
    POSITIVE LOGITS
    
    0.58
     gynhyrchwyd
    0.58
     way
    0.58
     five
    0.53
     snippetHide
    0.52
     öt
    0.51
    IsContent
    0.51
     seven
    0.49
     ujednoznacz
    0.49
     censiti
    0.49
    Activations Density 14.408%

    No Known Activations