© 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. 16319
    Prev
    Next
    INDEX
    Explanations

    historical recountings of people and events

    oai_token-act-pair · gemini-2.0-flash

    Is, are

    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
    Was
    -0.94
     was
    -0.91
    was
    -0.88
     Was
    -0.84
     were
    -0.75
     были
    -0.75
     была
    -0.72
     були
    -0.72
     kasarigan
    -0.71
    WAS
    -0.70
    POSITIVE LOGITS
     is
    1.38
     are
    0.88
     Is
    0.81
     am
    0.68
    is
    0.68
    Is
    0.68
     Are
    0.65
     ist
    0.64
    are
    0.63
     IS
    0.59
    Activations Density 2.835%

    No Known Activations