© 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. 7085
    Prev
    Next
    INDEX
    Explanations

    technical writing related to computer hardware, court cases, and quantum physics

    oai_token-act-pair · gemini-2.0-flash

    the word 'even'

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

    even

    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
     Theſe
    -0.83
     ſmall
    -0.68
     Jefus
    -0.64
     ſtate
    -0.64
     enfans
    -0.59
     pleaſure
    -0.58
     ſche
    -0.57
     beſt
    -0.57
     Yugoslav
    -0.57
     itſelf
    -0.56
    POSITIVE LOGITS
     even
    3.58
    even
    3.14
    Even
    2.67
     Even
    2.63
     EVEN
    2.47
     даже
    2.42
     навіть
    2.33
     incluso
    2.23
    EVEN
    2.23
     nawet
    2.19
    Activations Density 6.818%

    No Known Activations