© 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. 13966
    Prev
    Next
    INDEX
    Explanations

    location-based terms

    oai_token-act-pair · gemini-2.0-flash

    tism

    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
    DidLoad
    -0.56
     ſmall
    -0.55
     InkWell
    -0.55
    ftagPool
    -0.54
    ượu
    -0.53
    брь
    -0.53
    וך
    -0.53
     fometimes
    -0.53
    HtmlAttribute
    -0.52
    ologically
    -0.52
    POSITIVE LOGITS
    <bos>
    1.10
    OGND
    0.54
    UrlResolution
    0.52
    MessageOf
    0.49
    MessageTagHelper
    0.49
    ⓧ
    0.48
    Itoa
    0.48
    principalColumn
    0.48
    rungsseite
    0.47
    Personensuche
    0.47
    Activations Density 15.332%

    No Known Activations