© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2248
    Prev
    Next
    INDEX
    Explanations

    commas in the context of plans, logic and results

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Gegenteil
    -0.47
     (§
    -0.45
     herself
    -0.44
     yourselves
    -0.44
     abgerufen
    -0.43
     ihn
    -0.43
     Sop
    -0.42
     vri
    -0.42
     henne
    -0.41
     Anſ
    -0.41
    POSITIVE LOGITS
     we
    0.91
    Geplaatst
    0.84
     they
    0.82
    Personensuche
    0.82
    ніципа
    0.77
    GEBURTSDATUM
    0.77
    ɵɵ
    0.76
    MigrationBuilder
    0.74
     autorytatywna
    0.73
    fjspx
    0.69
    Activations Density 3.909%

    No Known Activations