© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15118
    Prev
    Next
    INDEX
    Explanations

    words and phrases that could indicate the beginning of something, such as "the first" or "result", but also picks up technical words.

    oai_token-act-pair · gemini-2.0-flash

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ‘
    -0.59
     '
    -0.56
     H
    -0.52
     “
    -0.50
    soort
    -0.47
     /
    -0.46
    ,
    -0.45
     "
    -0.45
    derung
    -0.45
    -0.42
    POSITIVE LOGITS
     Efq
    1.26
     raiſ
    1.05
     doubtnut
    0.99
     chofe
    0.97
     $_"
    0.97
     myſelf
    0.94
     uſed
    0.93
     Theſe
    0.93
     whoſe
    0.92
     ſta
    0.91
    Activations Density 11.229%
    No Known Activations