© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5671
    Prev
    Next
    INDEX
    Explanations

    words that denote a group, organization, or people, especially in a position of power or influence

    oai_token-act-pair · gemini-2.0-flash

    phrases related to sibling relationships

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

    Brothers

    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
    quiry
    -0.53
    rawDesc
    -0.52
     Markets
    -0.51
    #+#
    -0.51
     NSCoder
    -0.50
    politan
    -0.48
    jgl
    -0.47
     estekak
    -0.47
     MARKETS
    -0.47
     MARKET
    -0.46
    POSITIVE LOGITS
     brothers
    0.73
     brother
    0.71
    >::
    0.67
    })));
    0.62
    enterOuterAlt
    0.61
     BROS
    0.60
    brothers
    0.59
    олові
    0.58
     frères
    0.58
    %");
    0.57
    Activations Density 0.571%

    No Known Activations