© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12359
    Prev
    Next
    INDEX
    Explanations

    negative statements, often starting with "No"

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    RenderAtEndOf
    -0.74
    matchCondition
    -0.67
     GreatSchools
    -0.66
     '\\;'
    -0.62
    IntoConstraints
    -0.60
     Administrativna
    -0.59
     vermelhas
    -0.58
    Glück
    -0.57
     ItemStack
    -0.57
     &___
    -0.57
    POSITIVE LOGITS
    UserDao
    0.51
    hend
    0.51
    tagHelperRunner
    0.50
    IsContent
    0.49
    áln
    0.49
     Fa
    0.48
     mas
    0.48
    PhysRevD
    0.47
     S
    0.46
     Deum
    0.46
    Activations Density 5.703%

    No Known Activations