© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14668
    Prev
    Next
    INDEX
    Explanations

    common words that are frequently used in the English language

    oai_token-act-pair · gemini-2.0-flash

    Degree/quantity adverbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ConstraintMaker
    -0.62
    AllowAnonymous
    -0.60
    verwijspagina
    -0.59
     Anybody
    -0.58
    ThroughAttribute
    -0.58
    noinspection
    -0.56
    Anybody
    -0.56
    évaluateur
    -0.51
    нрави
    -0.50
     Everybody
    -0.49
    POSITIVE LOGITS
     bit
    1.15
     bits
    1.04
    proper
    1.03
    bit
    1.02
     proper
    0.97
     quite
    0.97
    quite
    0.95
     Quite
    0.93
    Proper
    0.92
    Quite
    0.92
    Activations Density 3.759%

    No Known Activations