© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11049
    Prev
    Next
    INDEX
    Explanations

    instances of feeling annoyed or irritated

    oai_token-act-pair · gemini-2.0-flash

    irritation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    GeneratedValue
    -0.50
    ControllerAdvice
    -0.45
     audience
    -0.44
     Normdatei
    -0.44
     gegeven
    -0.43
    Vidite
    -0.42
    unsplash
    -0.41
    lh
    -0.41
    ìa
    -0.41
    (<
    -0.40
    POSITIVE LOGITS
    Jeografia
    0.75
     Audiodateien
    0.75
    reszcie
    0.68
    MigrationBuilder
    0.68
    principalColumn
    0.63
    Diwedd
    0.61
    PreferredItem
    0.61
    bitField
    0.60
    expandindo
    0.58
    PRNewswire
    0.58
    Activations Density 0.687%

    No Known Activations