© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9669
    Prev
    Next
    INDEX
    Explanations

    references to figures or panels in scientific writing

    oai_token-act-pair · gemini-2.0-flash

    panel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     panel
    -3.03
     Panel
    -2.81
     panels
    -2.70
    panel
    -2.70
    Panel
    -2.59
     Panels
    -2.45
     PANEL
    -2.44
    PANEL
    -2.22
    panels
    -2.22
    Panels
    -2.09
    POSITIVE LOGITS
     فريبيس
    0.77
     Normdatei
    0.57
    omorphism
    0.57
    ագրություններ
    0.57
    atical
    0.54
     möge
    0.53
    inergic
    0.51
    ismet
    0.50
    исленность
    0.49
    LError
    0.49
    Activations Density 5.485%

    No Known Activations