© 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. 9058
    Prev
    Next
    INDEX
    Explanations

    words related to the mind or emotions

    oai_token-act-pair · gemini-2.0-flash

    mind/eye opening

    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
     Dimitri
    -0.41
    vri
    -0.40
     Cutting
    -0.39
     Vorder
    -0.37
    Cutting
    -0.37
    ีย
    -0.35
     Classe
    -0.35
     Timber
    -0.35
     cutting
    -0.34
     Lace
    -0.34
    POSITIVE LOGITS
     resourceCulture
    0.90
    GEBURTSDATUM
    0.85
     дописавши
    0.85
    stateProvider
    0.78
     ProtoMessage
    0.74
    ViewFeatures
    0.74
    رشف
    0.73
     propOrder
    0.72
    TypedDataSet
    0.72
     متعلقه
    0.71
    Activations Density 9.463%

    No Known Activations