© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7400
    Prev
    Next
    INDEX
    Explanations

    words related to coding and software/UI interfaces, with some bias toward non-English words

    oai_token-act-pair · gemini-2.0-flash

    code-related issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     herself
    -1.55
     she
    -1.28
     her
    -1.07
    herself
    -0.95
     ihrem
    -0.93
    但她
    -0.88
     internetowa
    -0.86
     그녀
    -0.85
    she
    -0.84
    她
    -0.84
    POSITIVE LOGITS
     himself
    1.28
     his
    1.13
    himself
    1.07
    his
    1.05
     seine
    0.84
     seiner
    0.79
     seinen
    0.79
    彼の
    0.77
    彼は
    0.77
    His
    0.75
    Activations Density 1.585%

    No Known Activations