© 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. 10093
    Prev
    Next
    INDEX
    Explanations

    movie reviews that mention names of actors, brands or designers in the fashion industry

    oai_token-act-pair · gemini-2.0-flash

    green

    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
     متعلقه
    -0.77
     nahilalakip
    -0.71
     насељу
    -0.65
    SequentialGroup
    -0.65
    uxxxx
    -0.63
    دانشنامهٔ
    -0.63
    SourceChecksum
    -0.62
     Wikimedijinoj
    -0.60
     العنوان
    -0.59
    KURZBESCHREIBUNG
    -0.59
    POSITIVE LOGITS
    goku
    0.49
     ethnic
    0.46
     Mugh
    0.44
     zari
    0.44
    interopRequire
    0.44
    }}/>
    0.43
    ropolitan
    0.43
     emulsion
    0.42
     muka
    0.42
    alui
    0.42
    Activations Density 0.655%

    No Known Activations