© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10098
    Prev
    Next
    INDEX
    Explanations

    content related to ski chairlifts

    oai_token-act-pair · gemini-2.0-flash

    Skiing/mountain related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     jadx
    -0.57
    MemoryWarning
    -0.55
    bootstrapcdn
    -0.54
     Jarvis
    -0.50
    ecake
    -0.48
     beginnetje
    -0.47
    ]>=
    -0.47
    onViewCreated
    -0.44
    MPL
    -0.43
    blockList
    -0.43
    POSITIVE LOGITS
     getopt
    0.62
    toPromise
    0.59
     TÉCNICA
    0.56
    findpost
    0.54
    rizona
    0.53
     Mission
    0.52
     TextInputType
    0.52
     Exacts
    0.51
    ‍♂️
    0.51
     BrowserModule
    0.50
    Activations Density 1.802%

    No Known Activations