© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3027
    Prev
    Next
    INDEX
    Explanations

    the word "cycle" and related terms, especially in relation to Peugeot car "i-Cockpit" settings or washing machine settings.

    oai_token-act-pair · gemini-2.0-flash

    configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    yntaxException
    -0.63
    plings
    -0.55
    RuleContext
    -0.54
    mbggenerated
    -0.52
     newOwner
    -0.51
    ])));
    -0.48
     ddelweddau
    -0.47
    TextFormField
    -0.47
    自立
    -0.47
    âtre
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.74
    basicConfig
    0.68
    .*")]
    0.64
     gynhyrchwyd
    0.63
     nakalista
    0.62
    Personensuche
    0.60
    
    0.55
    Sklici
    0.54
    <bos>
    0.53
    LookAnd
    0.53
    Activations Density 2.013%

    No Known Activations