© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7755
    Prev
    Next
    INDEX
    Explanations

    names that end in "andon" and words that express feelings

    oai_token-act-pair · gemini-2.0-flash

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    quently
    -0.53
     Efq
    -0.52
    Personensuche
    -0.50
    ToBounds
    -0.50
     nakalista
    -0.48
    WriteTagHelper
    -0.48
    ModelForm
    -0.47
     rağmen
    -0.47
     autorytatywna
    -0.47
    featureID
    -0.46
    POSITIVE LOGITS
     not
    1.63
    not
    1.32
     bukan
    1.26
     isn
    1.22
     Not
    1.18
     aren
    1.17
     nicht
    1.16
    不是
    1.09
     niet
    1.07
    Not
    1.05
    Activations Density 0.549%

    No Known Activations