© 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. 6355
    Prev
    Next
    INDEX
    Explanations

    text about bike trails

    oai_token-act-pair · gemini-2.0-flash

    cycle

    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
    EnableWeb
    -0.55
     وتسجيلات
    -0.51
     aérienne
    -0.51
     paard
    -0.51
    SwitchCompat
    -0.46
    وانات
    -0.45
     sportivo
    -0.45
    StreamWriter
    -0.45
    tgz
    -0.44
    eradish
    -0.44
    POSITIVE LOGITS
     cycle
    1.00
     cycles
    0.93
     Cycles
    0.93
     Cycle
    0.93
    Portale
    0.84
    cycle
    0.84
    Cycle
    0.83
     CYCLE
    0.82
    Kjelder
    0.79
    Cycles
    0.79
    Activations Density 1.642%

    No Known Activations