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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11470
    Prev
    Next
    INDEX
    Explanations

    text about real estate listings, especially ones that mention amenities and location

    oai_token-act-pair · gemini-2.0-flash

    terms related to shopping

    np_token-act-pair-logits · gpt-4o-mini

    Local places and things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    fjspx
    -0.63
    SourceChecksum
    -0.61
     nahilalakip
    -0.60
    Parcelize
    -0.55
     StatefulWidget
    -0.55
     ब्रेकडाउन
    -0.53
    tvguidetime
    -0.53
    idamente
    -0.52
    NUMX
    -0.51
    SEGUIR
    -0.49
    POSITIVE LOGITS
     shops
    0.64
    สา
    0.60
    hops
    0.59
    shops
    0.58
    ArrowToggle
    0.57
     malls
    0.56
    تقاوى
    0.53
     restaurants
    0.52
    cienti
    0.52
     inter
    0.51
    Activations Density 0.883%

    No Known Activations