© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10950
    Prev
    Next
    INDEX
    Explanations

    things that seem undesirable, like being tired, or imposing constraints

    oai_token-act-pair · gemini-2.0-flash

    tired or constraints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    AndEndTag
    -0.92
    kloped
    -0.80
     useStyles
    -0.72
    homonymie
    -0.69
    adaptiveStyles
    -0.68
    GEBURTSDATUM
    -0.68
    TypedDataSet
    -0.66
    SharedDtor
    -0.66
     TextAppearance
    -0.63
    ric
    -0.62
    POSITIVE LOGITS
    reszcie
    0.55
     ground
    0.50
     ogóle
    0.50
     którzy
    0.48
     flèche
    0.46
    diğinde
    0.45
     finally
    0.45
     sekali
    0.44
    ground
    0.44
    ')->
    0.44
    Activations Density 6.910%

    No Known Activations