© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9533
    Prev
    Next
    INDEX
    Explanations

    the word 'core' or words related to purchasing and fictional boys or mansions

    oai_token-act-pair · gemini-2.0-flash

    core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    MethodType
    -0.59
     razie
    -0.50
     AssemblyVersion
    -0.49
    bergement
    -0.46
    ệu
    -0.46
     cuisson
    -0.44
    rophore
    -0.44
    的一次
    -0.44
     yii
    -0.42
    UALA
    -0.42
    POSITIVE LOGITS
     estekak
    0.64
     okuyayım
    0.63
    ραν
    0.56
    publicain
    0.56
    boutin
    0.55
     يتيمه
    0.51
    litter
    0.51
    undur
    0.50
    PrototypeOf
    0.50
     indeb
    0.50
    Activations Density 0.284%

    No Known Activations