© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5414
    Prev
    Next
    INDEX
    Explanations

    blocks of C# code that work with JSON

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     TextAppearance
    -0.56
     shift
    -0.46
     واحد
    -0.44
     Advancement
    -0.44
     تومان
    -0.41
     advancement
    -0.40
     faults
    -0.40
     shifting
    -0.40
    dotta
    -0.40
    onAttach
    -0.40
    POSITIVE LOGITS
    SequentialGroup
    1.04
    GEBURTSDATUM
    0.93
    исленность
    0.91
    StoryboardSegue
    0.87
     ModelExpression
    0.85
    verwijspagina
    0.82
    Personensuche
    0.78
     تانيه
    0.76
     kasarigan
    0.74
    aarrggbb
    0.73
    Activations Density 2.688%

    No Known Activations