© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 15513
    Prev
    Next
    INDEX
    Explanations

    the words 'faster' and 'actions'

    oai_token-act-pair · gemini-2.0-flash

    processes, activities

    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
     way
    -0.85
    ,
    -0.85
    .
    -0.84
     a
    -0.81
     his
    -0.76
     the
    -0.73
     an
    -0.67
    veien
    -0.66
     this
    -0.65
     only
    -0.61
    POSITIVE LOGITS
    Personendaten
    1.02
     AttributeSet
    1.01
     ")");
    0.99
    )++;
    0.93
    KommentareTeilen
    0.91
    IContainer
    0.91
    tvguidetime
    0.89
     MainAxisSize
    0.89
    principalColumn
    0.88
    ?");
    0.87
    Activations Density 0.749%

    No Known Activations