© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13858
    Prev
    Next
    INDEX
    Explanations

    verbs describing movement or manipulation, and it is also activated by some nouns relating to celebration

    oai_token-act-pair · gemini-2.0-flash

    shaking and holding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     caufe
    -0.78
    ########.
    -0.76
     neceff
    -0.74
     purpoſe
    -0.74
     cauſe
    -0.72
     uſe
    -0.70
     obfer
    -0.68
    ukone
    -0.63
     raiſ
    -0.63
     مرئيه
    -0.62
    POSITIVE LOGITS
     treo
    0.64
    held
    0.55
    rifuge
    0.54
     held
    0.53
    setSubject
    0.52
    sträger
    0.52
     đựng
    0.49
    AxisAlignment
    0.48
     hold
    0.47
    letoe
    0.46
    Activations Density 2.406%

    No Known Activations