© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3281
    Prev
    Next
    INDEX
    Explanations

    words related to recipes or the description of fruit

    oai_token-act-pair · gemini-2.0-flash

    flavors

    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
     nahilalakip
    -0.63
    SequentialGroup
    -0.60
    例句
    -0.59
    HasForeignKey
    -0.56
    LookAnd
    -0.56
     Aubrey
    -0.55
    DrawerToggle
    -0.55
    ГЛА
    -0.54
    niająca
    -0.53
    GeneratedCode
    -0.53
    POSITIVE LOGITS
    RegistryLite
    0.66
     utafitiHapana
    0.52
    ImageContext
    0.47
     amp
    0.47
    msgTypes
    0.45
    त
    0.44
    ValueStyle
    0.44
    arti
    0.44
    Dichloroethene
    0.44
    Verde
    0.43
    Activations Density 3.861%

    No Known Activations