© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7107
    Prev
    Next
    INDEX
    Explanations

    words related to ancient kingdoms, empires, and royalty, and also words associated with combat or conflict.

    oai_token-act-pair · gemini-2.0-flash

    tvguidetime

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ngrx
    -0.62
     tender
    -0.57
     contextLoads
    -0.54
    HAEL
    -0.53
    pulumi
    -0.52
    EDEFAULT
    -0.52
     kark
    -0.51
    abbix
    -0.50
    heet
    -0.50
    TagHelper
    -0.50
    POSITIVE LOGITS
    tvguidetime
    0.72
    GEBURTSDATUM
    0.60
     formation
    0.56
    gameserver
    0.52
     Formation
    0.52
     FishBase
    0.52
     Formations
    0.52
     FORMATION
    0.51
     formations
    0.50
     Bioaccumulative
    0.49
    Activations Density 1.986%

    No Known Activations