© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7110
    Prev
    Next
    INDEX
    Explanations

    mentions of characters being defeated or destroyed

    oai_token-act-pair · gemini-2.0-flash

    destruction or damage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     дописавши
    -0.83
    MigrationBuilder
    -0.78
    UnusedPrivate
    -0.75
     indisponible
    -0.68
     fidé
    -0.68
     feroit
    -0.68
    BufferException
    -0.66
    uarga
    -0.66
    FTFY
    -0.66
    UnsafeEnabled
    -0.66
    POSITIVE LOGITS
     left
    0.50
     ripped
    0.49
    shutil
    0.48
    stad
    0.46
    getSystem
    0.46
    left
    0.45
     OMIT
    0.45
    supset
    0.44
    sm
    0.44
    RuleContext
    0.44
    Activations Density 2.256%

    No Known Activations