© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8235
    Prev
    Next
    INDEX
    Explanations

    language related to scheduling a consultation or appointment

    oai_token-act-pair · gemini-2.0-flash

    programming or technical terms related to appointments

    np_token-act-pair-logits · gpt-4o-mini

    scheduling appointments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ագրություններ
    -0.49
    lapsingToolbar
    -0.45
     CURLOPT
    -0.44
    actu
    -0.43
    retweeted
    -0.41
     trọng
    -0.40
     hoger
    -0.40
    PrimaryKey
    -0.39
    tamol
    -0.39
     gewo
    -0.38
    POSITIVE LOGITS
    GIVEREF
    0.68
    esModule
    0.67
    createCanvas
    0.66
    ValueStyle
    0.63
    BoxShadow
    0.62
    __':
    0.62
    enumi
    0.62
    ambique
    0.61
     оригіналу
    0.60
    __':
    0.59
    Activations Density 2.040%

    No Known Activations