© 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. 760
    Prev
    Next
    INDEX
    Explanations

    statements where someone is talking about a person's height

    oai_token-act-pair · gemini-2.0-flash

    dimensions

    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
     height
    -2.17
     Height
    -2.11
     lift
    -1.93
     Lift
    -1.92
     HEIGHT
    -1.91
    Height
    -1.89
     heights
    -1.85
    height
    -1.83
    Lift
    -1.83
     lifting
    -1.81
    POSITIVE LOGITS
     виправивши
    0.52
    figer
    0.51
     فريبيس
    0.48
    onnay
    0.48
    ijnen
    0.48
     gratuite
    0.47
     SafeMath
    0.47
    ης
    0.44
    begre
    0.43
    obacz
    0.43
    Activations Density 1.327%

    No Known Activations