© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11205
    Prev
    Next
    INDEX
    Explanations

    technical writing and chemical terminology

    oai_token-act-pair · gemini-2.0-flash

    scientific and technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    +:+
    -0.73
    GeneratedMessage
    -0.66
    
    -0.65
    StoryboardSegue
    -0.63
    ValueStyle
    -0.57
     nakalista
    -0.57
    DebuggerNonUser
    -0.54
    mybatisplus
    -0.52
    NgModule
    -0.52
    signable
    -0.52
    POSITIVE LOGITS
     때문
    0.54
     yle
    0.48
     fratello
    0.47
     okuyayım
    0.45
    áját
    0.45
     compless
    0.45
    clientHeight
    0.44
    य
    0.44
     חיצוניים
    0.44
    ----</
    0.44
    Activations Density 3.456%

    No Known Activations