© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3850
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash

    ,

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -5.00
    ,
    -4.00
     (
    -3.98
     I
    -3.61
     a
    -3.55
     the
    -3.50
     in
    -3.42
    <eos>
    -3.34
     "
    -3.33
     A
    -3.27
    POSITIVE LOGITS
     myſelf
    8.06
     itſelf
    7.78
     Efq
    7.75
     Monfieur
    7.63
     Majefty
    7.16
     pleaſure
    7.13
     Jefus
    7.06
     purpoſe
    7.03
     Theſe
    7.03
     Anſ
    6.88
    Activations Density 7.205%

    No Known Activations