© 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. 14650
    Prev
    Next
    INDEX
    Explanations

    sentences with multiple clauses separated by commas or conjunctions and containing a form of the verb "to be."

    oai_token-act-pair · gemini-2.0-flash

    fragments of code or programming terminology

    np_token-act-pair-logits · gpt-4o-mini
    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
    mleri
    -0.53
    @
    -0.47
    ucie
    -0.42
    setViewName
    -0.40
     parte
    -0.40
    ่านั้น
    -0.39
     proper
    -0.39
     at
    -0.39
    لے
    -0.39
    estable
    -0.38
    POSITIVE LOGITS
    AddHtmlAttribute
    0.94
    contentLoaded
    0.84
     Wikimedijinoj
    0.82
    oredCriteria
    0.81
    Personensuche
    0.81
    __*/
    0.79
    tonsoft
    0.79
     BoxFit
    0.77
     BorderSide
    0.77
    IndentedString
    0.76
    Activations Density 2.662%

    No Known Activations