© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3715
    Prev
    Next
    INDEX
    Explanations

    accreditation information about architecture programs

    oai_token-act-pair · gemini-2.0-flash

    selection panels

    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
     flu
    -0.50
    tops
    -0.49
     typos
    -0.45
    rativa
    -0.44
     mow
    -0.43
     refrigerators
    -0.43
     Oblig
    -0.43
     Dispens
    -0.43
    Flu
    -0.43
    matchCondition
    -0.43
    POSITIVE LOGITS
     panels
    0.71
     EconPapers
    0.71
    ReusableCell
    0.70
    évaluateur
    0.69
     panel
    0.69
     Normdatei
    0.68
    AccessorTable
    0.68
     interview
    0.68
     committee
    0.68
    panels
    0.67
    Activations Density 1.457%

    No Known Activations