© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11940
    Prev
    Next
    INDEX
    Explanations

    mentions of methods and tools used in material analysis

    oai_token-act-pair · gemini-2.0-flash

    scientific material analysis

    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
     متعلقه
    -0.75
     CanadaChoose
    -0.60
    BeginInit
    -0.57
     unknownFields
    -0.56
    batore
    -0.55
    ఔ
    -0.54
    enumi
    -0.52
     doInBackground
    -0.52
    makeText
    -0.52
    HandlerContext
    -0.50
    POSITIVE LOGITS
     Exacts
    0.57
    IsContent
    0.56
     iridescent
    0.50
    AspectRatio
    0.48
    bootstrapcdn
    0.48
    ropical
    0.47
     exhibit
    0.47
     anastom
    0.47
     dissipated
    0.47
    WriteAttribute
    0.47
    Activations Density 11.379%

    No Known Activations