© 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. 16363
    Prev
    Next
    INDEX
    Explanations

    code snippets and configuration file entries

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
    ,
    -1.21
     Efq
    -0.85
     Majefty
    -0.84
    contentLoaded
    -0.84
     ſtate
    -0.83
     purpoſe
    -0.82
     ſta
    -0.80
     poffe
    -0.79
     myſelf
    -0.79
     themſelves
    -0.79
    POSITIVE LOGITS
    מבר
    0.48
    InstanceState
    0.45
     Inc
    0.44
    ですよ
    0.43
    inck
    0.42
    erein
    0.41
    rollo
    0.41
     Zacks
    0.41
    inc
    0.40
    OrCreate
    0.40
    Activations Density 2.898%

    No Known Activations