© 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. 8207
    Prev
    Next
    INDEX
    Explanations

    proper nouns belonging to organizations and people involved in media production

    oai_token-act-pair · gemini-2.0-flash

    TV/Film Networks

    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
     تضيفلها
    -0.75
    ResumeLayout
    -0.69
    ValueStyle
    -0.66
    GeneratedCode
    -0.59
    eriks
    -0.56
    casila
    -0.56
    rollable
    -0.54
    ьаж
    -0.54
    PerformLayout
    -0.54
    writeField
    -0.52
    POSITIVE LOGITS
    TagMode
    0.51
    StoryboardSegue
    0.50
     JpaRepository
    0.50
     itſelf
    0.46
    dawnictwo
    0.43
    tillery
    0.43
    naments
    0.41
     SIMBAD
    0.41
    ſelf
    0.41
     typelib
    0.40
    Activations Density 5.979%

    No Known Activations