© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14330
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to location, especially cities and poorer neighborhoods, as well as words that describe research findings.

    oai_token-act-pair · gemini-2.0-flash

    geographic areas/locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     مض
    -0.47
    фом
    -0.43
    Flags
    -0.42
     tort
    -0.41
     تض
    -0.41
     Anschluss
    -0.41
    ADORA
    -0.40
    Host
    -0.40
     Say
    -0.40
    hind
    -0.39
    POSITIVE LOGITS
     area
    1.13
    StoryboardSegue
    1.04
     areas
    1.03
     AREA
    1.02
     Areas
    1.02
     Area
    1.00
    Area
    0.98
    areas
    0.98
     AREAS
    0.98
    area
    0.93
    Activations Density 3.504%

    No Known Activations