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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4685
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "to be"

    oai_token-act-pair · gemini-2.0-flash

    negative situations

    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
     nakalista
    -0.58
    Demografia
    -0.57
    üstü
    -0.56
    ┗
    -0.56
    suke
    -0.55
    BRI
    -0.54
    ppur
    -0.54
     Wikisource
    -0.53
    apunov
    -0.53
     trapped
    -0.51
    POSITIVE LOGITS
    localctx
    0.59
    <bos>
    0.57
    DebuggerNonUser
    0.54
    tagext
    0.53
    exitRule
    0.50
    parsedMessage
    0.50
    WireFormatLite
    0.48
    دانشنامهٔ
    0.47
    oredCriteria
    0.47
     AssemblyTitle
    0.46
    Activations Density 8.324%

    No Known Activations