© 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. 13036
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of turning things on and off

    oai_token-act-pair · gemini-2.0-flash

    on/off

    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
     purpoſe
    -0.95
    ValueStyle
    -0.90
    parsedMessage
    -0.88
     مرئيه
    -0.86
    ſelves
    -0.85
     Efq
    -0.84
     houſe
    -0.83
    ſelf
    -0.82
    Zeneca
    -0.81
     pleaſure
    -0.81
    POSITIVE LOGITS
     ON
    1.49
     On
    1.47
     off
    1.37
    On
    1.31
    ON
    1.30
     Off
    1.26
    Off
    1.18
    on
    1.16
     OFF
    1.15
     on
    1.14
    Activations Density 2.798%

    No Known Activations