© 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. 12954
    Prev
    Next
    INDEX
    Explanations

    descriptions of outdoor trails

    oai_token-act-pair · gemini-2.0-flash

    Hiking and outdoor trails

    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
    makeConstraints
    -0.52
    Kanpo
    -0.49
     referenties
    -0.49
    oa̍t
    -0.48
     trail
    -0.48
    Trail
    -0.46
    RTEE
    -0.45
     TRAIL
    -0.44
    trail
    -0.43
     arşivlendi
    -0.42
    POSITIVE LOGITS
     ProtoMessage
    0.84
    
    0.69
    parsedMessage
    0.64
     noDo
    0.59
    zogen
    0.57
     Bureau
    0.56
    ProcessEvent
    0.56
    VYMaps
    0.56
    antaranya
    0.56
    pogon
    0.56
    Activations Density 2.157%

    No Known Activations