© 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. 4877
    Prev
    Next
    INDEX
    Explanations

    uses and comparisons of "less" and "more"

    oai_token-act-pair · gemini-2.0-flash

    less

    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
    tagHelperRunner
    -0.93
     متعلقه
    -0.89
    IndentedString
    -0.88
     myſelf
    -0.88
     propOrder
    -0.88
     تضيفلها
    -0.85
     Jefus
    -0.84
    bootstrapcdn
    -0.82
    StoryboardSegue
    -0.82
     ſche
    -0.80
    POSITIVE LOGITS
     an
    0.44
     cost
    0.37
     promising
    0.36
     quan
    0.35
     but
    0.35
    ARD
    0.34
    licher
    0.34
    ว่า
    0.34
     advanced
    0.34
     which
    0.34
    Activations Density 3.108%

    No Known Activations