© 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. 6954
    Prev
    Next
    INDEX
    Explanations

    sentences that transition to a conclusion

    oai_token-act-pair · gemini-2.0-flash

    variations of "stand"

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

    stand

    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
    хьтан
    -0.52
     úteis
    -0.51
    řit
    -0.50
    acyjne
    -0.50
     bedien
    -0.49
    inatal
    -0.49
     IndexPath
    -0.49
    campal
    -0.48
    קישורים
    -0.47
     Ceinture
    -0.47
    POSITIVE LOGITS
     stand
    3.61
     STAND
    3.23
     Stand
    3.23
     stands
    3.20
     stood
    3.13
    Stand
    2.98
     standing
    2.95
    stand
    2.88
     Stands
    2.81
    stands
    2.67
    Activations Density 2.359%

    No Known Activations