© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6114
    Prev
    Next
    INDEX
    Explanations

    a mix of terms including "time", crime" and "name"

    oai_token-act-pair · gemini-2.0-flash

    Time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Theſe
    -0.98
     Anſ
    -0.96
    StoryboardSegue
    -0.93
    IUrlHelper
    -0.92
     Reſ
    -0.90
     ſche
    -0.90
     ―――――
    -0.89
     ſeveral
    -0.89
     raiſ
    -0.88
     Jefus
    -0.88
    POSITIVE LOGITS
    machus
    0.50
     
    0.50
     voort
    0.47
     (
    0.45
     C
    0.44
     single
    0.43
     so
    0.41
     sub
    0.41
     umum
    0.41
     trans
    0.40
    Activations Density 1.062%

    No Known Activations