© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7305
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words "well", "good", and comparative adjectives.

    oai_token-act-pair · gemini-2.0-flash

    well

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     AssemblyCulture
    -0.96
     TextInputType
    -0.73
     Roskov
    -0.66
    الحياه
    -0.65
    Much
    -0.63
    bootstrapcdn
    -0.63
     AssemblyTitle
    -0.61
     Wikimedijinoj
    -0.60
    ArgsConstructor
    -0.59
    kloped
    -0.59
    POSITIVE LOGITS
    |}
    0.47
    hoga
    0.47
    </thead>
    0.45
    RG
    0.44
    škas
    0.44
    colnshire
    0.44
     acquainted
    0.43
    方的
    0.43
    emp
    0.42
    rc
    0.42
    Activations Density 1.689%

    No Known Activations