© 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. 4271
    Prev
    Next
    INDEX
    Explanations

    technical terms relating to AC/DC power conversion

    oai_token-act-pair · gemini-2.0-flash

    power conversion

    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
    contentLoaded
    -0.80
     consultato
    -0.80
    SequentialGroup
    -0.54
     Mehl
    -0.54
    HostException
    -0.52
    WebElementEntity
    -0.51
     estekak
    -0.49
    uthor
    -0.48
     concedes
    -0.47
    poh
    -0.47
    POSITIVE LOGITS
     BrowserModule
    0.56
     InputDecoration
    0.54
    TestingModule
    0.54
    #+#
    0.48
     centrifugal
    0.47
    ixels
    0.47
    UIControl
    0.46
     PropTypes
    0.45
    PullParser
    0.45
    ]")]
    0.45
    Activations Density 7.217%

    No Known Activations