© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 390
    Prev
    Next
    INDEX
    Explanations

    references to Marijuana laws and culture

    oai_token-act-pair · gemini-2.0-flash

    marijuana/cannabis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    enumi
    -0.79
    expandindo
    -0.78
    </tfoot>
    -0.77
    __*/
    -0.75
    AndEndTag
    -0.74
    /**
    -0.69
     Audiodateien
    -0.68
     disambiguazione
    -0.68
     Numerade
    -0.67
    +:+
    -0.67
    POSITIVE LOGITS
     activity
    0.47
     virus
    0.41
     BNF
    0.40
     activities
    0.40
     Activity
    0.40
     mil
    0.40
    usan
    0.40
    ONA
    0.39
    dor
    0.38
    mil
    0.38
    Activations Density 0.844%

    No Known Activations