© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5156
    Prev
    Next
    INDEX
    Explanations

    relatively common words that connect clauses/sentences.

    oai_token-act-pair · gemini-2.0-flash

    code 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    two
    -0.75
    three
    -0.69
     two
    -0.69
     två
    -0.67
     deux
    -0.67
    #+#
    -0.66
     trois
    -0.65
    +#+
    -0.65
     three
    -0.63
    Two
    -0.63
    POSITIVE LOGITS
     
    2.20
     
    
    0.67
    .)}
    0.48
    \}=
    0.47
    %")
    0.46
     Thirty
    0.45
     about
    0.45
     Twenty
    0.44
    esten
    0.43
     Forty
    0.41
    Activations Density 5.567%

    No Known Activations