© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9921
    Prev
    Next
    INDEX
    Explanations

    parts of words that might be prefixes or suffixes, as well as other short, common word fragments.

    oai_token-act-pair · gemini-2.0-flash

    symbols and punctuation in structured data

    np_token-act-pair-logits · gpt-4o-mini

    technical and legal text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    
    -0.96
     CURIAM
    -0.95
     Efq
    -0.93
     <=",
    -0.91
     photolibrary
    -0.90
    ^(@)
    -0.90
     Theſe
    -0.89
    .")
    -0.88
     Jefus
    -0.88
    }}}
    -0.88
    POSITIVE LOGITS
    :
    0.56
     
    0.55
    rs
    0.48
     (
    0.48
    (
    0.47
    -
    0.46
    _
    0.45
    p
    0.45
     &
    0.45
    amp
    0.45
    Activations Density 1.047%

    No Known Activations