© 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. 7490
    Prev
    Next
    INDEX
    Explanations

    words related to complex bureaucratic scientific or political documents.

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or tags

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

    scientific/technical processes

    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
    การ
    -0.54
     Fä
    -0.47
    ÉR
    -0.45
     inputs
    -0.45
    throws
    -0.44
     fra
    -0.44
     нака
    -0.43
     Tre
    -0.43
     fine
    -0.43
     Dis
    -0.43
    POSITIVE LOGITS
    AddTagHelper
    0.96
     CreateTagHelper
    0.94
    ItemBackground
    0.88
    AndEndTag
    0.84
     pleaſure
    0.82
    styleType
    0.82
    rungsseite
    0.81
     tartalomajánló
    0.80
     larmes
    0.78
     enfans
    0.78
    Activations Density 4.403%

    No Known Activations