© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12368
    Prev
    Next
    INDEX
    Explanations

    words or parts of words that are often used as suffixes

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Monfieur
    -1.40
     myſelf
    -1.34
     Efq
    -1.30
     itſelf
    -1.27
     Theſe
    -1.26
     ſeveral
    -1.24
     becauſe
    -1.22
     Cæsar
    -1.19
     Jefus
    -1.17
     himſelf
    -1.16
    POSITIVE LOGITS
    en
    0.43
    ca
    0.40
     ка
    0.39
    aca
    0.37
    ki
    0.35
    me
    0.35
    gar
    0.35
    ть
    0.34
    vi
    0.33
    ante
    0.33
    Activations Density 18.308%

    No Known Activations