© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2635
    Prev
    Next
    INDEX
    Explanations

    code and scientific writing

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks indicating exclamations or questions

    np_token-act-pair-logits · gpt-4o-mini

    Emphasis punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    contentLoaded
    -1.02
    
    -0.98
    OrBuilder
    -0.94
     Roskov
    -0.94
    IsContent
    -0.90
    })`
    -0.90
    complexContent
    -0.89
    ,:);
    -0.89
    PerformLayout
    -0.89
    }\]
    -0.89
    POSITIVE LOGITS
    !
    2.55
    ?
    2.42
    ?!
    2.39
    !?
    2.23
    !!
    1.98
    !!!
    1.91
    ?!?
    1.77
     !
    1.76
    ?!"
    1.75
    ?!?!
    1.75
    Activations Density 18.182%

    No Known Activations