© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13575
    Prev
    Next
    INDEX
    Explanations

    code related to building Android apps

    oai_token-act-pair · gemini-2.0-flash

    programming code

    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
     Ch
    -0.79
     Ma
    -0.75
     Val
    -0.72
     At
    -0.69
     For
    -0.68
     Lo
    -0.66
     Me
    -0.65
     Cho
    -0.65
     Pal
    -0.65
     Mon
    -0.64
    POSITIVE LOGITS
     Monfieur
    1.09
     purpoſe
    0.96
     itſelf
    0.91
     Efq
    0.89
     Anſ
    0.89
     Theſe
    0.87
     Diſ
    0.82
     houſe
    0.80
     Reſ
    0.79
     ſeveral
    0.79
    Activations Density 1.115%

    No Known Activations