© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8754
    Prev
    Next
    INDEX
    Explanations

    vulgar emotional language related to the mouth and eyes

    oai_token-act-pair · gemini-2.0-flash

    shutting eyes/mouths; secrecy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     riuscito
    -0.54
    niosek
    -0.52
     sucedido
    -0.50
    migrationBuilder
    -0.50
    html
    -0.44
    הערות
    -0.41
     belts
    -0.40
    urz
    -0.39
     redeemed
    -0.39
    ~
    -0.39
    POSITIVE LOGITS
     silence
    1.18
     silent
    1.06
     Silence
    1.01
    silence
    0.96
    Silence
    0.93
     Silent
    0.92
    silent
    0.88
    Silent
    0.86
     silently
    0.83
     Quiet
    0.83
    Activations Density 0.676%

    No Known Activations