© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3347
    Prev
    Next
    INDEX
    Explanations

    verbs in the present progressive or active voice, sometimes in relation to a specific subject.

    oai_token-act-pair · gemini-2.0-flash

    terms related to financial summaries or planning

    np_token-act-pair-logits · gpt-4o-mini

    news/events updates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ostavi
    -0.67
     يتيمه
    -0.60
     collègues
    -0.55
     carreaux
    -0.54
     termites
    -0.54
     convidados
    -0.54
     Particles
    -0.52
     ingrédients
    -0.50
     invités
    -0.50
     étapes
    -0.50
    POSITIVE LOGITS
     budgets
    0.76
     debuts
    0.64
     lists
    0.62
     schedules
    0.60
     plots
    0.60
    afficheront
    0.59
     tours
    0.59
     Budgets
    0.58
     szóci
    0.58
     bans
    0.57
    Activations Density 7.833%

    No Known Activations