© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6286
    Prev
    Next
    INDEX
    Explanations

    road, highway, and interstate names and numbers.

    oai_token-act-pair · gemini-2.0-flash

    places and roads

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    rrggbb
    -0.67
    InvalidProtocol
    -0.61
     Савезне
    -0.60
     sánh
    -0.60
    argout
    -0.58
    AttributeSet
    -0.57
     <<<<<<<<<<<<<<
    -0.57
     initState
    -0.56
     noqa
    -0.55
     cref
    -0.54
    POSITIVE LOGITS
     Patna
    0.54
     ground
    0.53
     park
    0.52
     writeTo
    0.50
     Parks
    0.49
     Troy
    0.49
    parks
    0.48
    oaks
    0.48
     ramp
    0.48
    Parks
    0.48
    Activations Density 8.752%

    No Known Activations