© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12480
    Prev
    Next
    INDEX
    Explanations

    phrases used when making a legal argument or stating a legal conclusion.

    oai_token-act-pair · gemini-2.0-flash

    Forms of "had"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    adaptiveStyles
    -0.64
    SourceChecksum
    -0.56
    hotra
    -0.56
     tartalomajánló
    -0.56
     TestBed
    -0.55
    FieldBuilder
    -0.53
    nitus
    -0.52
    omock
    -0.50
    liferay
    -0.50
     ostavi
    -0.49
    POSITIVE LOGITS
     had
    2.75
    Had
    2.52
     Had
    2.47
    had
    2.42
     HAD
    1.94
    HAD
    1.59
     avaient
    1.55
     hadde
    1.52
     hatte
    1.50
     hatten
    1.50
    Activations Density 4.021%

    No Known Activations