© 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. 3380
    Prev
    Next
    INDEX
    Explanations

    configuration file settings

    oai_token-act-pair · gemini-2.0-flash

    plus symbol

    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
    +
    -1.16
    +),
    -0.96
    +)
    -0.90
    +,
    -0.90
    + 
    -0.87
     Plus
    -0.84
    +]
    -0.82
    <bos>
    -0.77
    +.
    -0.77
    plus
    -0.75
    POSITIVE LOGITS
     Arquivado
    0.58
     Arhivirano
    0.55
     enfans
    0.54
    ☛
    0.54
    下一篇
    0.54
     Insee
    0.54
     câncer
    0.54
    Legături
    0.54
    __(/*!
    0.54
    USTR
    0.53
    Activations Density 0.632%

    No Known Activations