© 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. 6031
    Prev
    Next
    INDEX
    Explanations

    first person accounts debugging code or describing customer interactions

    oai_token-act-pair · gemini-2.0-flash

    "something" and articles

    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
    PreferredItem
    -0.75
     Administrativna
    -0.69
    mybatisplus
    -0.69
    Anything
    -0.68
    anything
    -0.67
    StoryboardSegue
    -0.67
     nicio
    -0.66
     محفوظة
    -0.64
    adaptiveStyles
    -0.64
     protoimpl
    -0.63
    POSITIVE LOGITS
     something
    0.80
     some
    0.70
    Something
    0.69
    something
    0.69
     Something
    0.66
     an
    0.65
     a
    0.59
     etwas
    0.54
     Some
    0.53
     SOMETHING
    0.52
    Activations Density 3.900%

    No Known Activations