© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12772
    Prev
    Next
    INDEX
    Explanations

    abbreviations and seemingly random two-letter strings

    oai_token-act-pair · gemini-2.0-flash

    URLs and code

    np_max-act-logits · gemini-2.0-flash

    say "subword fragments"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    E
    -0.91
    O
    -0.89
    IntoConstraints
    -0.82
    tvguidetime
    -0.75
    ECH
    -0.75
    EES
    -0.70
    EH
    -0.69
    EAN
    -0.69
    tigo
    -0.67
    OIS
    -0.66
    POSITIVE LOGITS
    principalColumn
    0.47
     goutte
    0.47
     financières
    0.47
     sauvages
    0.46
     verticales
    0.45
     météo
    0.45
     مواليد
    0.44
     jelasnya
    0.44
     noires
    0.44
    brite
    0.44
    Activations Density 2.316%

    No Known Activations