© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4366
    Prev
    Next
    INDEX
    Explanations

    mentions of height, especially heights of people

    oai_token-act-pair · gemini-2.0-flash

    Detects "short"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    EndInit
    -0.68
     démission
    -0.66
     *++
    -0.66
    principalTable
    -0.65
     inalámbrico
    -0.65
     FishBase
    -0.65
    Хьажоргаш
    -0.64
    BeginInit
    -0.64
     ExecuteAsync
    -0.64
     négociations
    -0.64
    POSITIVE LOGITS
     short
    1.17
     shorter
    1.04
     Short
    0.94
    short
    0.94
    Short
    0.93
     shor
    0.90
     shortest
    0.88
     SHORT
    0.87
     six
    0.82
     stock
    0.73
    Activations Density 1.499%

    No Known Activations