© 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. 2646
    Prev
    Next
    INDEX
    Explanations

    text discussing avoiding military service and medical evaluations

    oai_token-act-pair · gemini-2.0-flash

    drafting and revisions

    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
     draft
    -2.50
     Draft
    -2.44
    Draft
    -2.30
    draft
    -2.19
     DRAFT
    -2.17
     drafts
    -2.09
    DRAFT
    -1.98
     Dra
    -1.91
     drafted
    -1.83
     drafting
    -1.82
    POSITIVE LOGITS
    TestingModule
    0.71
     HasFactory
    0.59
    nanoTime
    0.56
    ENOMEM
    0.55
    BorderStyle
    0.55
    FieldOffset
    0.54
    InstanceState
    0.50
     partij
    0.50
    osgi
    0.49
    WebpackPlugin
    0.49
    Activations Density 2.187%

    No Known Activations