© 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. 15076
    Prev
    Next
    INDEX
    Explanations

    words related to work and jobs, especially manual labor.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash

    say "▁" tokens

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     resourceCulture
    -1.13
    RenderAtEndOf
    -1.12
    ValueStyle
    -1.10
     متعلقه
    -1.09
    ніципа
    -1.06
     CanadaChoose
    -1.05
    MigrationBuilder
    -1.04
    UnusedPrivate
    -1.02
    ьаж
    -1.01
    DockStyle
    -1.01
    POSITIVE LOGITS
     avoient
    0.17
     čierna
    0.13
     enfans
    0.13
     étoient
    0.12
    <bos>
    0.12
     étoit
    0.11
     regionales
    0.05
     světě
    0.05
     esclavos
    0.04
     princí
    0.04
    Activations Density 74.857%

    No Known Activations