© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3907
    Prev
    Next
    INDEX
    Explanations

    general purpose verbs and pronouns

    oai_token-act-pair · gemini-2.0-flash

    do/doing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    InjectAttribute
    -0.73
    iastes
    -0.55
    ficulties
    -0.55
    ]--;
    -0.54
    IsContent
    -0.53
    windowFixed
    -0.52
    ENIX
    -0.51
     parch
    -0.50
    lifier
    -0.50
    Geplaatst
    -0.50
    POSITIVE LOGITS
     doing
    1.30
    Doing
    1.21
    doing
    1.19
     Doing
    1.19
     DOING
    1.04
     doin
    0.98
     done
    0.84
    done
    0.75
     Done
    0.73
     do
    0.72
    Activations Density 2.998%

    No Known Activations