© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12622
    Prev
    Next
    INDEX
    Explanations

    words about liking or enjoying something

    oai_token-act-pair · gemini-2.0-flash

    loved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    '
    -0.68
    ↵↵
    -0.60
    -
    -0.59
    ’
    -0.56
    and
    -0.56
    (
    -0.55
    #
    -0.54
     (
    -0.54
    .
    -0.53
    And
    -0.50
    POSITIVE LOGITS
    Portály
    1.20
     propOrder
    1.18
     FetchType
    1.14
    enterOuterAlt
    1.11
    Sucesor
    1.08
     MainAxisSize
    1.08
     enfans
    1.05
    ]")]
    1.04
    Geplaatst
    1.02
    ]='\
    1.02
    Activations Density 0.319%

    No Known Activations