© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4591
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest improbability or something that is not expected

    oai_token-act-pair · gemini-2.0-flash

    hypothetical/unexpected situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Παραπομπές
    -0.71
     suivants
    -0.64
    stretchr
    -0.62
    AndEndTag
    -0.61
     réguli
    -0.61
     africains
    -0.60
    XmlAccessType
    -0.59
    CloseOperation
    -0.59
     avoient
    -0.59
     BorderRadius
    -0.57
    POSITIVE LOGITS
    <bos>
    0.67
    ronpa
    0.50
    mosis
    0.47
     ২০১
    0.46
    الإنجليزية
    0.46
     desp
    0.45
    dersfield
    0.44
    tvguidetime
    0.43
    CreateModel
    0.43
    wix
    0.43
    Activations Density 0.811%

    No Known Activations