© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10895
    Prev
    Next
    INDEX
    Explanations

    phrases that compare or contrast two things

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating existence or state

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

    a/an

    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
     different
    -1.45
    other
    -1.42
     other
    -1.42
    different
    -1.39
     Different
    -1.36
    Different
    -1.35
     Other
    -1.23
    Other
    -1.23
     andere
    -1.21
    OTHER
    -1.20
    POSITIVE LOGITS
     a
    1.18
    rungsseite
    0.52
    hagic
    0.48
    ⓧ
    0.43
     an
    0.43
    texttt
    0.43
    ibouti
    0.43
    a
    0.42
    inot
    0.42
    pF
    0.41
    Activations Density 1.090%

    No Known Activations