© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13535
    Prev
    Next
    INDEX
    Explanations

    hedged statements where the speaker is trying to explain or justify something

    oai_token-act-pair · gemini-2.0-flash

    basically or much

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    LETIN
    -0.50
    DTD
    -0.49
     apparently
    -0.49
    apparently
    -0.47
     Moslem
    -0.46
    tagHelperRunner
    -0.44
     basically
    -0.44
     photolibrary
    -0.43
     Dasar
    -0.42
    ValueGeneration
    -0.42
    POSITIVE LOGITS
    createNewFile
    0.76
    jaro
    0.71
    antiation
    0.71
     tramonto
    0.68
    çalves
    0.68
     GenerationType
    0.67
    aneity
    0.65
    مثلة
    0.65
    ctum
    0.64
    tiérrez
    0.63
    Activations Density 3.910%

    No Known Activations