© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9680
    Prev
    Next
    INDEX
    Explanations

    phrases including prepositions and numbers that suggest measurement, degree or comparison

    oai_token-act-pair · gemini-2.0-flash

    percentages and approximations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     للمعارف
    -1.08
     itſelf
    -0.84
    uxxxx
    -0.76
     myſelf
    -0.74
    存于互联网档案馆
    -0.72
    ViewFeatures
    -0.70
     betweenstory
    -0.69
    ſelf
    -0.69
     Jefus
    -0.69
    StructEnd
    -0.68
    POSITIVE LOGITS
     livet
    0.44
    RequestOptions
    0.43
    borderWidth
    0.43
     
    0.42
    VolleyError
    0.42
    brokes
    0.42
    냈
    0.41
    yt
    0.40
     «
    0.40
     إنتاج
    0.40
    Activations Density 1.189%

    No Known Activations