© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13619
    Prev
    Next
    INDEX
    Explanations

    language related to poetry or music with both positive and negative sentiments

    oai_token-act-pair · gemini-2.0-flash

    structured phrases or terms resembling song lyrics

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     snippetHide
    -0.83
    بوابة
    -0.81
     StatefulWidget
    -0.77
    adpleegd
    -0.74
    complexContent
    -0.73
    #+#
    -0.70
    featureID
    -0.70
    TagMode
    -0.69
    MigrationBuilder
    -0.67
    LookAnd
    -0.66
    POSITIVE LOGITS
    ,
    0.48
     zij
    0.47
    THEY
    0.45
     tilla
    0.44
     Until
    0.44
    permitAll
    0.44
     utente
    0.43
     incomplète
    0.43
    hower
    0.42
    Until
    0.41
    Activations Density 9.639%

    No Known Activations