© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13890
    Prev
    Next
    INDEX
    Explanations

    descriptive botanical language

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Signalez
    -0.80
    SourceChecksum
    -0.80
    EndContext
    -0.78
     nakalista
    -0.78
     Waray
    -0.71
    tvguidetime
    -0.70
     allAfrica
    -0.70
    ----</
    -0.68
     surla
    -0.68
    enumi
    -0.67
    POSITIVE LOGITS
     uncin
    0.48
     fusca
    0.46
    NegativeButton
    0.42
     californ
    0.42
     vej
    0.42
     recensement
    0.41
     Venise
    0.41
     neceff
    0.41
    hase
    0.40
    CreateInfo
    0.39
    Activations Density 1.017%

    No Known Activations