© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15560
    Prev
    Next
    INDEX
    Explanations

    words related to influence or enforcement

    oai_token-act-pair · gemini-2.0-flash

    context or pressure-related actions or states

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

    say "on"

    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
    Negative Logits
     upon
    -2.34
    upon
    -1.77
     on
    -1.67
     Upon
    -1.66
     UPON
    -1.64
    Upon
    -1.55
     vpon
    -1.12
     asupra
    -1.09
     на
    -1.05
     auf
    -1.05
    POSITIVE LOGITS
    parsedMessage
    1.23
    AndEndTag
    1.16
    \{\\
    1.13
    RenderAtEndOf
    1.13
    enumii
    1.09
    StoryboardSegue
    1.08
     للمعارف
    1.08
     kasarigan
    1.05
     Drapeau
    1.05
     Мексичка
    1.05
    Activations Density 0.465%

    No Known Activations