© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14712
    Prev
    Next
    INDEX
    Explanations

    code or function definitions

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Roskov
    -0.71
    __(/*!
    -0.58
     quoted
    -0.54
     disponibilités
    -0.53
    createTextNode
    -0.52
    Rüyada
    -0.48
    icordia
    -0.47
    namics
    -0.47
     CSM
    -0.47
    deniz
    -0.46
    POSITIVE LOGITS
    +#+#
    0.71
    fjspx
    0.63
    RTLD
    0.59
    PMailer
    0.58
    <bos>
    0.57
    SharedCtor
    0.57
    LookAnd
    0.55
    UserScript
    0.55
     gloire
    0.55
    Données
    0.54
    Activations Density 2.292%

    No Known Activations