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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10481
    Prev
    Next
    INDEX
    Explanations

    code snippets, including file paths, imports, and variables

    oai_token-act-pair · gemini-2.0-flash

    source code

    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
     preſent
    -0.70
     pleaſure
    -0.68
     Anſ
    -0.67
     Hift
    -0.64
     Reſ
    -0.62
     faſt
    -0.61
     Theſe
    -0.60
     purpoſe
    -0.60
     Diſ
    -0.59
     Supremo
    -0.58
    POSITIVE LOGITS
     resourceCulture
    1.02
    CppMethod
    0.89
    ReusableCell
    0.89
    HtmlAttribute
    0.86
    WireFormat
    0.81
    TemporalType
    0.80
    UnusedPrivate
    0.76
    parsedMessage
    0.74
    GenerationType
    0.73
    rungsseite
    0.73
    Activations Density 13.728%

    No Known Activations