© 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. 5314
    Prev
    Next
    INDEX
    Explanations

    markers of personal narratives, like personal pronouns, question words, and conjunctions

    oai_token-act-pair · gemini-2.0-flash

    which

    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
    ph
    -0.47
    j
    -0.45
    E
    -0.44
    Z
    -0.42
    z
    -0.41
    war
    -0.40
    M
    -0.40
    1
    -0.40
    ec
    -0.39
     (
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.94
    StoryboardSegue
    0.93
     HasFactory
    0.93
     isComment
    0.93
    styleType
    0.90
    Hauptartikel
    0.90
    tagHelperRunner
    0.89
     kasarigan
    0.88
    ReusableCell
    0.87
    хьтан
    0.86
    Activations Density 1.813%

    No Known Activations