© 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. 5547
    Prev
    Next
    INDEX
    Explanations

    words related to politics and government

    oai_token-act-pair · gemini-2.0-flash

    references to politics and consulting

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

    political news

    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
    évaluateur
    -0.75
     Roskov
    -0.75
    endpush
    -0.70
    #+#
    -0.67
    webElementXpaths
    -0.66
    openqa
    -0.66
    StoryboardSegue
    -0.65
    IContainer
    -0.63
     Wicidata
    -0.61
    LayoutStyle
    -0.61
    POSITIVE LOGITS
     nakalista
    0.69
    });*/
    0.48
    IVEREF
    0.48
    };*/
    0.48
     base
    0.48
    Base
    0.46
    clonal
    0.45
    })*/
    0.45
     general
    0.45
    AI
    0.44
    Activations Density 2.620%

    No Known Activations