© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4394
    Prev
    Next
    INDEX
    Explanations

    words relating to medical diagnostics and pathology

    oai_token-act-pair · gemini-2.0-flash

    Changes and findings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     iprot
    -0.53
     nakalista
    -0.49
    principalColumn
    -0.46
     AssemblyCulture
    -0.45
    mbggenerated
    -0.45
    conuts
    -0.45
    ValueStyle
    -0.44
    brew
    -0.43
     manuten
    -0.42
     nutz
    -0.41
    POSITIVE LOGITS
     changes
    0.87
     Changes
    0.78
    changes
    0.74
    Changes
    0.69
     change
    0.68
     CHANGES
    0.65
     findings
    0.64
     Findings
    0.64
     Change
    0.63
    Change
    0.62
    Activations Density 4.010%

    No Known Activations