© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2984
    Prev
    Next
    INDEX
    Explanations

    code syntax and Objective-C/Java keywords

    oai_token-act-pair · gemini-2.0-flash

    Foreign language words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     LK
    -0.68
    hematical
    -0.67
     embodi
    -0.66
     hearted
    -0.65
     hyperplasia
    -0.65
     Kyrgyz
    -0.65
     Rukh
    -0.65
     heterosexual
    -0.64
     tabular
    -0.64
     pelvis
    -0.64
    POSITIVE LOGITS
      
    0.48
    import
    0.37
     varandra
    0.36
     stället
    0.35
     daß
    0.35
    "
    0.35
     prossima
    0.35
     prochaine
    0.35
    })(
    0.34
    Die
    0.34
    Activations Density 5.768%

    No Known Activations