© 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. 15957
    Prev
    Next
    INDEX
    Explanations

    trails and rivers

    oai_token-act-pair · gemini-2.0-flash

    river

    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
    ISupport
    -0.70
     للمعارف
    -0.67
    yntaxException
    -0.66
    ècie
    -0.60
     hangers
    -0.57
     magasiner
    -0.56
     AssemblyTitle
    -0.56
     hanger
    -0.55
     الحره
    -0.55
    DebuggerStep
    -0.55
    POSITIVE LOGITS
     autorytatywna
    0.62
    GEBURTS
    0.55
    boat
    0.47
    wal
    0.47
    chase
    0.47
    dal
    0.46
    ագրություններ
    0.46
    pare
    0.44
     cá
    0.44
    AndEndTag
    0.43
    Activations Density 1.921%

    No Known Activations