© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12666
    Prev
    Next
    INDEX
    Explanations

    the words "last", "next", "this", "that", "another" and "year"

    oai_token-act-pair · gemini-2.0-flash

    say "year"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -1.30
     uſed
    -1.23
     myſelf
    -1.23
     itſelf
    -1.22
     Monfieur
    -1.20
     doubtnut
    -1.19
     Majefty
    -1.19
    ſelf
    -1.19
    wiſe
    -1.14
    ſelves
    -1.13
    POSITIVE LOGITS
     y
    0.66
     Y
    0.49
     F
    0.46
    ↵
    0.46
     ya
    0.46
    ↵↵
    0.45
     He
    0.44
     
    0.43
     yer
    0.42
    F
    0.42
    Activations Density 1.605%

    No Known Activations