© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12992
    Prev
    Next
    INDEX
    Explanations

    a mix of proper nouns, geographic place names, job titles or academic fields, and math symbols/equations

    oai_token-act-pair · gemini-2.0-flash

    organizations and people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     autorytatywna
    -0.73
    +#+
    -0.71
    MENAFN
    -0.68
    VersionUID
    -0.67
    LEIA
    -0.66
    zzleHttp
    -0.65
     OGS
    -0.62
     يتيمه
    -0.61
     lenker
    -0.60
    titure
    -0.59
    POSITIVE LOGITS
    zy
    0.48
    homonymie
    0.48
    tagHelper
    0.44
    fi
    0.44
    iau
    0.41
     Does
    0.40
    inov
    0.40
     prefeitura
    0.39
     zou
    0.39
     szükség
    0.38
    Activations Density 4.911%

    No Known Activations