© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7781
    Prev
    Next
    INDEX
    Explanations

    text about teaching and talking to prospective employers or about students defending their faith

    oai_token-act-pair · gemini-2.0-flash

    presentation

    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
    ciclop
    -0.53
     Paral
    -0.50
    Turn
    -0.47
     khóa
    -0.46
    endurch
    -0.45
    clud
    -0.45
    })_{
    -0.45
     Colchester
    -0.45
    diac
    -0.44
    Sour
    -0.44
    POSITIVE LOGITS
     presenting
    1.26
     presentation
    1.22
     presentations
    1.16
    Presenting
    1.14
     Presenting
    1.09
     Presentation
    1.07
     présentation
    1.02
     Presentations
    1.02
    presentation
    1.01
     presentazione
    0.99
    Activations Density 0.998%

    No Known Activations