© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15649
    Prev
    Next
    INDEX
    Explanations

    mentions of recreational outdoor facilities

    oai_token-act-pair · gemini-2.0-flash

    Parks and 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
     Himo
    -0.47
    tský
    -0.45
    UnitTesting
    -0.44
    ServiceModel
    -0.44
     Modelling
    -0.43
     Modeling
    -0.43
     scoring
    -0.43
    СТИ
    -0.42
    setItem
    -0.42
    UnsafeEnabled
    -0.41
    POSITIVE LOGITS
     BoxDecoration
    0.69
    httphttps
    0.58
    SerializedSize
    0.56
    Izvori
    0.55
    Atoi
    0.55
    ⓧ
    0.53
    laught
    0.52
    Kesimpulan
    0.52
    bibinfo
    0.49
    :✨
    0.49
    Activations Density 3.692%

    No Known Activations