© 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. 3908
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to broadcasting and news production

    oai_token-act-pair · gemini-2.0-flash

    Technical device descriptions

    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
     equip
    -0.67
     Equip
    -0.63
    equipped
    -0.62
    EQUIPMENT
    -0.61
     MACHINE
    -0.61
     &___
    -0.61
     apparatus
    -0.60
     operation
    -0.60
     install
    -0.60
     Equipment
    -0.60
    POSITIVE LOGITS
    tagHelperRunner
    0.73
     Roskov
    0.65
     AssemblyCulture
    0.62
     <=",
    0.58
    IVEREF
    0.53
    UnsafeEnabled
    0.53
    IUrlHelper
    0.53
    InitVars
    0.52
    ficulty
    0.50
    MemoryWarning
    0.49
    Activations Density 7.044%

    No Known Activations