© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4418
    Prev
    Next
    INDEX
    Explanations

    words that indicate association, connection, reliance or helping.

    oai_token-act-pair · gemini-2.0-flash

    Specific entities and opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ômico
    -0.71
     afuera
    -0.64
    setVerticalGroup
    -0.61
     esposo
    -0.60
    ɚ
    -0.59
     econô
    -0.58
     CreateTagHelper
    -0.57
    ValueStyle
    -0.57
    ônimo
    -0.56
     agregar
    -0.55
    POSITIVE LOGITS
     £
    0.74
     Cllr
    0.68
    tershire
    0.68
    ilí
    0.67
     nearer
    0.66
     Yorkshire
    0.65
     Welsh
    0.64
    trous
    0.64
     Lambeth
    0.63
     pupils
    0.63
    Activations Density 4.483%

    No Known Activations