© 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. 13857
    Prev
    Next
    INDEX
    Explanations

    references to people and locations, often with dates or other identifiers surrounding the names.

    oai_token-act-pair · gemini-2.0-flash

    references to "Indian" or "chief."

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

    Native American/Indian

    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
    rosine
    -0.48
     Ciencia
    -0.45
     Barbosa
    -0.42
     mitral
    -0.42
    Brainz
    -0.41
    clipboard
    -0.41
     Yeast
    -0.41
     crossword
    -0.41
    ligence
    -0.41
     Citron
    -0.41
    POSITIVE LOGITS
     Indian
    1.18
    Indian
    1.10
     chief
    1.07
     INDIAN
    1.06
     Chief
    1.04
    Chief
    1.03
    chief
    1.02
     indian
    1.01
     Indians
    1.00
     CHIEF
    1.00
    Activations Density 1.852%

    No Known Activations