© 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. 4303
    Prev
    Next
    INDEX
    Explanations

    statements about something happening rarely now, though it once wasn't

    oai_token-act-pair · gemini-2.0-flash

    rare

    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
    AndEndTag
    -0.67
    NewUrlParser
    -0.59
    ModelForm
    -0.56
    sidemargin
    -0.54
    AntiForgeryToken
    -0.54
    CodedInputStream
    -0.54
     CreateTagHelper
    -0.54
    offsetof
    -0.50
     ErrIntOverflow
    -0.50
     newOwner
    -0.50
    POSITIVE LOGITS
     rare
    2.45
    Rare
    2.16
    rare
    2.09
     Rare
    2.06
     rarity
    2.00
     uncommon
    1.95
     rarer
    1.95
     rarest
    1.88
     RARE
    1.85
     rarely
    1.78
    Activations Density 1.876%

    No Known Activations