© 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. 11923
    Prev
    Next
    INDEX
    Explanations

    words indicating a distinction or selection

    oai_token-act-pair · gemini-2.0-flash

    differences

    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
     виправивши
    -0.71
    بوابة
    -0.71
    <bos>
    -0.66
     pinulongan
    -0.66
    HasAnnotation
    -0.62
     незавершена
    -0.62
    enderror
    -0.60
    دانشنامهٔ
    -0.60
    tagHelperRunner
    -0.60
    httphttps
    -0.60
    POSITIVE LOGITS
     purpoſe
    0.60
     Houſe
    0.60
     ſtate
    0.60
     myſelf
    0.59
     *++
    0.59
     Conſ
    0.57
     ſy
    0.55
     ſp
    0.55
     theſe
    0.54
     unſ
    0.53
    Activations Density 1.133%

    No Known Activations