© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2915
    Prev
    Next
    INDEX
    Explanations

    the word "acculturation", sometimes with the prefix "de"

    oai_token-act-pair · gemini-2.0-flash

    terms related to programming or data structures

    np_token-act-pair-logits · gpt-4o-mini

    acc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     يتيمه
    -0.65
    SourceChecksum
    -0.60
    iedenis
    -0.55
    thalt
    -0.54
    addCriterion
    -0.51
     LEY
    -0.51
    MENAFN
    -0.51
     Alva
    -0.50
    tanleria
    -0.50
    اشتم
    -0.50
    POSITIVE LOGITS
     ProtoMessage
    0.51
     CommonModule
    0.51
     ThemeData
    0.49
    chossen
    0.47
    Referanser
    0.47
     információk
    0.47
    ObjectContext
    0.47
    chalten
    0.45
     civile
    0.45
    GeneratedValue
    0.45
    Activations Density 0.735%

    No Known Activations