© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16289
    Prev
    Next
    INDEX
    Explanations

    words related to material properties or medical support and implements

    oai_token-act-pair · gemini-2.0-flash

    firmness and texture

    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
     TAMBÉM
    -0.76
    ModelAdmin
    -0.72
    onAttach
    -0.71
    findpost
    -0.63
    protoimpl
    -0.60
     المعيارى
    -0.60
     EconPapers
    -0.59
    tioners
    -0.58
    RegistryLite
    -0.58
    onViewCreated
    -0.58
    POSITIVE LOGITS
     hard
    0.85
    hard
    0.84
     hardness
    0.79
    Hard
    0.75
     Hard
    0.74
    tough
    0.71
    HARD
    0.71
    硬
    0.70
     tough
    0.70
    Hardness
    0.69
    Activations Density 0.762%

    No Known Activations