© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11329
    Prev
    Next
    INDEX
    Explanations

    names of people and pronouns when family drama is happening

    oai_token-act-pair · gemini-2.0-flash

    verbs

    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
     requested
    -0.53
    exitRule
    -0.48
     asked
    -0.47
     presented
    -0.47
     entered
    -0.47
     posted
    -0.47
     teased
    -0.45
     added
    -0.44
     tested
    -0.44
     submitted
    -0.44
    POSITIVE LOGITS
     shoots
    0.80
     notices
    0.78
     deposits
    0.78
     suggests
    0.78
     hooks
    0.78
     plots
    0.77
     lists
    0.77
     mentions
    0.77
     tells
    0.76
     watches
    0.75
    Activations Density 1.608%

    No Known Activations