© 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. 4884
    Prev
    Next
    INDEX
    Explanations

    words related to software or the Czech Republic

    oai_token-act-pair · gemini-2.0-flash

    Machine code

    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
     I
    -0.53
     reda
    -0.50
    __':
    -0.50
    出版年
    -0.49
     des
    -0.48
     de
    -0.47
     no
    -0.47
    Whilst
    -0.47
     leren
    -0.46
     banderas
    -0.46
    POSITIVE LOGITS
     Majefty
    1.05
     Efq
    0.98
     Мексичка
    0.93
     $_"
    0.91
     poffe
    0.88
     Jefus
    0.85
     Anſ
    0.85
     Shakspeare
    0.84
     Shaksp
    0.82
     Monfieur
    0.82
    Activations Density 0.065%

    No Known Activations