© 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. 14296
    Prev
    Next
    INDEX
    Explanations

    references to people, especially those who are prominent or in a position of influence.

    oai_token-act-pair · gemini-2.0-flash

    prominent adjectives describing individuals

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

    highly skilled person

    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
    maid
    -0.48
     devolver
    -0.43
     Extragalactic
    -0.43
     Minaj
    -0.42
    uszcz
    -0.42
     apret
    -0.42
     forfeit
    -0.40
    ẾT
    -0.40
    esez
    -0.39
    czaj
    -0.39
    POSITIVE LOGITS
     eminent
    1.20
     renowned
    1.14
     experienced
    1.14
     famous
    1.13
     prominent
    1.08
     talented
    1.06
     legendary
    1.05
     accomplished
    1.04
     great
    1.02
     veteran
    0.98
    Activations Density 2.469%

    No Known Activations