© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    words discussing research and developing that research in recent times

    oai_token-act-pair · gemini-2.0-flash

    Research papers

    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
     ISNI
    -0.57
    numerusform
    -0.55
    pria
    -0.53
     autorytatywna
    -0.52
     sopr
    -0.52
     ArrayAdapter
    -0.52
    ComponentScan
    -0.51
    omla
    -0.51
    AddWithValue
    -0.50
    FromArgb
    -0.49
    POSITIVE LOGITS
    følgelig
    0.58
     Roskov
    0.53
    saraba
    0.52
    IVersion
    0.51
    انه
    0.48
    Spoljašnje
    0.47
     vieille
    0.47
    PHeader
    0.45
     rural
    0.45
    ாள
    0.45
    Activations Density 3.322%

    No Known Activations