© 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. 4662
    Prev
    Next
    INDEX
    Explanations

    small sentence fragments involving function words and content words in a specific order.

    oai_token-act-pair · gemini-2.0-flash

    generally, rule

    np_max-act-logits · 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
     مشين
    -0.81
    
    -0.77
    homonymie
    -0.76
     <>",
    -0.76
    GEBURTS
    -0.72
    AndEndTag
    -0.67
     MwSt
    -0.66
     AssemblyTitle
    -0.65
    +#+#
    -0.65
    InputBorder
    -0.64
    POSITIVE LOGITS
     generally
    1.46
    generally
    1.24
     rule
    1.23
     Generally
    1.17
    Generally
    1.17
     mostly
    1.13
    rule
    1.06
     правило
    1.05
    Mostly
    0.98
     general
    0.97
    Activations Density 1.171%

    No Known Activations