© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14507
    Prev
    Next
    INDEX
    Explanations

    superscripted numbers and punctuated sentence endings

    oai_token-act-pair · gemini-2.0-flash

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    cati
    -0.49
    Tahoma
    -0.48
    obec
    -0.47
     Settle
    -0.44
     ihres
    -0.42
    tely
    -0.42
    عيد
    -0.41
    nościo
    -0.40
    upon
    -0.40
     emas
    -0.40
    POSITIVE LOGITS
     Roskov
    0.91
    aarrggbb
    0.89
     Normdatei
    0.88
    IndentedString
    0.87
     typelib
    0.87
    GEBURTSDATUM
    0.86
     autorytatywna
    0.86
    IntoConstraints
    0.84
    хьтан
    0.84
     protoimpl
    0.84
    Activations Density 1.658%

    No Known Activations