© 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. 6975
    Prev
    Next
    INDEX
    Explanations

    clauses beginning with but/it and phrases indicating personal opinions.

    oai_token-act-pair · gemini-2.0-flash

    it

    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
    DockStyle
    -0.76
    исленность
    -0.74
    الإنجليزية
    -0.73
    quelize
    -0.71
    StructEnd
    -0.70
     Detta
    -0.69
    клопе
    -0.68
    CodedInputStream
    -0.67
    kloped
    -0.67
    Бахар
    -0.66
    POSITIVE LOGITS
     it
    1.48
     It
    1.12
    It
    1.05
    it
    0.88
    มัน
    0.78
     nó
    0.77
    它
    0.76
     оно
    0.72
     usarlo
    0.58
     farlo
    0.56
    Activations Density 2.120%

    No Known Activations