© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12179
    Prev
    Next
    INDEX
    Explanations

    words related to building materials and the earth

    oai_token-act-pair · 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
     lenker
    -0.85
    SequentialGroup
    -0.74
    <bos>
    -0.71
    @[+][
    -0.67
    Rujuakan
    -0.58
    NamedQueries
    -0.58
    PickerController
    -0.57
    complexContent
    -0.57
    StandardCharsets
    -0.57
    XmlAccessType
    -0.56
    POSITIVE LOGITS
     iſt
    0.55
     Theſe
    0.54
     GenerationType
    0.53
     Efq
    0.53
     myſelf
    0.52
     tombstone
    0.50
     wors
    0.50
    󠁴
    0.50
     Fais
    0.49
     ſche
    0.49
    Activations Density 0.845%

    No Known Activations