© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16267
    Prev
    Next
    INDEX
    Explanations

    references to the earth, and possibly also safety

    oai_token-act-pair · gemini-2.0-flash

    earth or safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     étoient
    -0.75
     juridiques
    -0.74
     policiales
    -0.71
     mourut
    -0.71
     étoit
    -0.70
     judiciales
    -0.69
     avoient
    -0.69
     Juifs
    -0.68
     vectorielle
    -0.66
     térm
    -0.65
    POSITIVE LOGITS
    ########.
    0.70
     special
    0.62
    %")
    0.60
    PLEX
    0.58
    iencing
    0.58
    acry
    0.58
    ้าว
    0.58
    ButtonPressed
    0.57
     beginnetje
    0.57
    معلومات
    0.57
    Activations Density 1.269%

    No Known Activations