© 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. 2639
    Prev
    Next
    INDEX
    Explanations

    points in a speech or story

    oai_token-act-pair · gemini-2.0-flash

    technical or programming keywords

    np_token-act-pair-logits · gpt-4o-mini
    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
     its
    -0.50
    Song
    -0.43
     Mores
    -0.43
    Twas
    -0.43
    它的
    -0.42
    μαι
    -0.41
     Milk
    -0.41
    라이
    -0.41
     Ogil
    -0.40
     оно
    -0.40
    POSITIVE LOGITS
    NOPQRST
    0.76
    enumii
    0.69
    verifyException
    0.67
    expandindo
    0.66
    AndroidJUnit
    0.65
     htons
    0.64
    RUnlock
    0.63
    WRP
    0.61
     ddelweddau
    0.60
     parseFrom
    0.59
    Activations Density 1.582%

    No Known Activations