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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6927
    Prev
    Next
    INDEX
    Explanations

    code snippets, location related words and time related words

    oai_token-act-pair · gemini-2.0-flash

    file/plugin location

    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
     location
    -2.92
     Location
    -2.86
    location
    -2.78
    Location
    -2.75
     locations
    -2.69
     LOCATION
    -2.59
     Locations
    -2.59
    locations
    -2.52
    Locations
    -2.52
    LOCATION
    -2.45
    POSITIVE LOGITS
     مشين
    0.55
     resourceCulture
    0.54
    chitis
    0.53
    IsMutable
    0.52
     bezeichneter
    0.52
    ✷
    0.51
     Exacts
    0.50
     ComVisible
    0.50
     Firth
    0.50
    تماد
    0.49
    Activations Density 2.939%

    No Known Activations