© 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. 14663
    Prev
    Next
    INDEX
    Explanations

    sequences of words detailing crimes or police activity, and also phrases about planning an adaptation of something.

    oai_token-act-pair · gemini-2.0-flash

    crime and awards

    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
    ag
    -0.44
    j
    -0.43
    vec
    -0.43
     chacun
    -0.42
    o
    -0.42
    und
    -0.41
     exerted
    -0.41
    esos
    -0.41
    a
    -0.41
     vec
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    1.04
    WriteTagHelper
    1.00
     propOrder
    0.98
     myſelf
    0.95
     autorytatywna
    0.94
     '\\;'
    0.93
    XmlAccessType
    0.91
     Efq
    0.91
     beginnetje
    0.90
     AspNetCore
    0.90
    Activations Density 2.152%

    No Known Activations