© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14306
    Prev
    Next
    INDEX
    Explanations

    various topics like health, furniture, energy and blogging

    oai_token-act-pair · gemini-2.0-flash

    too

    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
     also
    -2.92
    also
    -2.63
    Also
    -2.55
     Also
    -2.44
     también
    -2.19
     também
    -2.16
     также
    -2.03
     juga
    -2.00
     også
    -1.99
     també
    -1.95
    POSITIVE LOGITS
     too
    0.95
    too
    0.70
     demasiado
    0.64
     Too
    0.60
    Too
    0.59
     TOO
    0.58
    UniformLocation
    0.47
     terlalu
    0.47
    ContextHolder
    0.44
     zwar
    0.44
    Activations Density 3.148%

    No Known Activations