© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14731
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "real" in the context of real estate

    oai_token-act-pair · gemini-2.0-flash

    real

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    REAL
    -0.58
     REAL
    -0.57
    Real
    -0.56
    Welt
    -0.56
     Real
    -0.54
    real
    -0.53
    welt
    -0.49
     Welt
    -0.48
     LIFE
    -0.46
    World
    -0.46
    POSITIVE LOGITS
     myſelf
    0.86
    imetry
    0.83
    @[+][
    0.82
     purpoſe
    0.80
     InputDecoration
    0.80
    NameInMap
    0.79
     &___
    0.79
     Theſe
    0.77
     himſelf
    0.77
    帖最后由
    0.77
    Activations Density 3.372%

    No Known Activations