© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12767
    Prev
    Next
    INDEX
    Explanations

    references to professional infrastructure engineering

    oai_token-act-pair · gemini-2.0-flash

    professional service and companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     ujednoznacz
    -0.50
     SwitchCompat
    -0.47
     Hire
    -0.46
     contract
    -0.45
     contractors
    -0.44
    Contract
    -0.44
     TestBed
    -0.44
     contractor
    -0.43
    onLoad
    -0.43
    namic
    -0.42
    POSITIVE LOGITS
     تضيفلها
    0.70
    InstanceState
    0.65
    tagHelperRunner
    0.64
    +#+#
    0.64
     LCCN
    0.63
     csoport
    0.61
    FieldBuilder
    0.61
    ContentAsync
    0.60
     كومونز
    0.60
    StructEnd
    0.59
    Activations Density 3.237%

    No Known Activations