© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13307
    Prev
    Next
    INDEX
    Explanations

    phrases that involve negation, requirement, or possibility

    oai_token-act-pair · gemini-2.0-flash

    negation or conditionality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    cannot
    -0.68
    must
    -0.66
     must
    -0.64
     Cannot
    -0.63
    Must
    -0.60
     Must
    -0.58
     cannot
    -0.58
    Cannot
    -0.57
    <bos>
    -0.54
    gotta
    -0.54
    POSITIVE LOGITS
    reactivex
    0.64
    tableFuture
    0.63
    UnusedPrivate
    0.60
    ifolium
    0.57
     NgModule
    0.57
     kaynağından
    0.56
    AMPLE
    0.54
    
    0.54
    rungsseite
    0.54
    即可
    0.53
    Activations Density 3.339%

    No Known Activations