© 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. 12840
    Prev
    Next
    INDEX
    Explanations

    equations and descriptions of data from scientific studies

    oai_token-act-pair · 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
    legi
    -0.42
     traccia
    -0.42
     cielos
    -0.42
     muun
    -0.41
    Abstra
    -0.40
     siglos
    -0.39
    ;->
    -0.39
     particuliers
    -0.39
     blusas
    -0.39
     toàn
    -0.38
    POSITIVE LOGITS
     Majefty
    0.88
     تانيه
    0.88
     ་་
    0.84
     houſe
    0.84
    IsContent
    0.84
    iastes
    0.82
    __':
    0.82
    contentLoaded
    0.80
     doubtnut
    0.80
     AssemblyVersion
    0.79
    Activations Density 19.386%

    No Known Activations