© 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. 2033
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "you" and related words or references to the reader

    oai_token-act-pair · gemini-2.0-flash

    words related to navigating choices

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

    personal feelings

    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
     الحره
    -0.84
    OGND
    -0.76
    CodedInputStream
    -0.74
    adaptiveStyles
    -0.72
     ModelExpression
    -0.71
     ISNI
    -0.70
    Personensuche
    -0.69
     متعلقه
    -0.69
    Билгалдахарш
    -0.68
     ainfi
    -0.68
    POSITIVE LOGITS
     fallen
    0.48
     rush
    0.47
    ddress
    0.46
     falling
    0.46
     fell
    0.45
     ض
    0.44
     squ
    0.43
     falls
    0.43
     miss
    0.43
     wal
    0.42
    Activations Density 2.014%

    No Known Activations