© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15580
    Prev
    Next
    INDEX
    Explanations

    instances where something is being expressed, defined, stated, or disclosed

    oai_token-act-pair · gemini-2.0-flash

    expressed

    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
    +#+#
    -1.16
     étoit
    -1.04
     depicted
    -1.04
     shown
    -1.02
    PreferredItem
    -1.00
     GenerationType
    -0.99
     HasFactory
    -0.98
     ainfi
    -0.98
     présentés
    -0.96
    ValueStyle
    -0.96
    POSITIVE LOGITS
     di
    0.81
     de
    0.79
     ‘
    0.69
     “
    0.69
     der
    0.69
    <eos>
    0.68
     re
    0.67
     an
    0.66
     "
    0.66
     den
    0.65
    Activations Density 2.156%

    No Known Activations