© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15185
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to abstract concepts that humans can experience

    oai_token-act-pair · gemini-2.0-flash

    Abstract/philosophical concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     FormControl
    -0.48
    ican
    -0.46
    Passcode
    -0.45
    ApiController
    -0.44
    ATOS
    -0.44
    ActiveRecord
    -0.43
    basicConfig
    -0.43
     blant
    -0.42
    moveToFirst
    -0.42
     femmin
    -0.41
    POSITIVE LOGITS
    <bos>
    0.87
     насељу
    0.76
     unknownFields
    0.66
    UrlResolution
    0.58
    EndGlobalSection
    0.57
     newBuilder
    0.55
     CURIAM
    0.50
    .*")]
    0.50
    IUrlHelper
    0.49
    RuleContext
    0.48
    Activations Density 7.366%

    No Known Activations