© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14238
    Prev
    Next
    INDEX
    Explanations

    words related to marketing

    oai_token-act-pair · gemini-2.0-flash

    targeting business clients

    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
     AppModule
    -0.86
    migrationBuilder
    -0.80
     Anſ
    -0.79
    EDEFAULT
    -0.78
    İstinadlar
    -0.78
     Conſ
    -0.76
    WriteBarrier
    -0.75
     Diſ
    -0.75
     Majefty
    -0.74
     tartalomajánló
    -0.74
    POSITIVE LOGITS
    atrième
    0.53
     clients
    0.49
     ne
    0.47
     would
    0.45
     فال
    0.44
     memer
    0.43
     c
    0.42
     ra
    0.42
    [--
    0.42
     pro
    0.42
    Activations Density 2.053%

    No Known Activations