© 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. 7671
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to vehicle parts, especially braking systems

    oai_token-act-pair · gemini-2.0-flash

    Car crashes and technicalities

    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
     crash
    -1.80
     Crash
    -1.74
    Crash
    -1.64
     crashed
    -1.57
    crash
    -1.53
     crashes
    -1.50
     crashing
    -1.45
     Cras
    -1.28
     collision
    -1.27
     Collision
    -1.17
    POSITIVE LOGITS
     oprot
    0.61
     iVar
    0.57
    CodeAttribute
    0.56
    ształ
    0.52
    esModule
    0.52
    έρα
    0.51
     verification
    0.51
    yntaxException
    0.49
    uxxxx
    0.49
    oara
    0.49
    Activations Density 2.483%

    No Known Activations