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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6323
    Prev
    Next
    INDEX
    Explanations

    words related to statistical analysis and computer programming.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'where'

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

    where

    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
    ---|---|
    -0.51
    それと
    -0.42
    ypep
    -0.41
    ftime
    -0.40
     BorderRadius
    -0.40
    ertes
    -0.40
    íra
    -0.40
    τως
    -0.39
     eje
    -0.39
    kelijkheid
    -0.38
    POSITIVE LOGITS
     where
    3.42
    where
    3.13
    Where
    2.75
     Where
    2.70
     donde
    2.44
     WHERE
    2.42
     où
    2.38
    donde
    2.19
     где
    2.17
    WHERE
    2.16
    Activations Density 6.039%

    No Known Activations