© 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. 7905
    Prev
    Next
    INDEX
    Explanations

    several words and phrases related to baseball.

    oai_token-act-pair · gemini-2.0-flash

    words related to flying

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

    flying

    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
    -1.04
    ValueStyle
    -0.78
     للمعارف
    -0.75
     Efq
    -0.75
    脚注の使い方
    -0.74
    ########.
    -0.67
    ſelf
    -0.64
     ainfi
    -0.64
     purpoſe
    -0.64
    Clik
    -0.63
    POSITIVE LOGITS
     flight
    0.67
     flights
    0.60
     fly
    0.60
     disc
    0.58
     flies
    0.57
     flew
    0.56
    Disc
    0.55
     flying
    0.55
    disc
    0.53
     Fly
    0.53
    Activations Density 1.221%

    No Known Activations