© 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. 446
    Prev
    Next
    INDEX
    Explanations

    words or short phrases which express opinions, arguments, or reactions

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    帖最后由
    -0.57
    +#+#
    -0.53
    #+#
    -0.52
    specialchars
    -0.48
    RectangleBorder
    -0.48
     Commencez
    -0.47
     protoimpl
    -0.47
     Réalisation
    -0.47
    niająca
    -0.46
     ProtoMessage
    -0.46
    POSITIVE LOGITS
    },[])
    0.51
     Waray
    0.48
    BeginInit
    0.48
     pinulongan
    0.48
    CodeDom
    0.48
     soprav
    0.48
    gebob
    0.47
    Diweddarwch
    0.47
    liceerd
    0.46
     /\.
    0.46
    Activations Density 37.459%

    No Known Activations