© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14700
    Prev
    Next
    INDEX
    Explanations

    source code and related elements like file paths, code blocks, and version-related information

    oai_token-act-pair · gemini-2.0-flash

    Code/data delimiters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IsContent
    -0.38
    tvguidetime
    -0.33
    />
    -0.32
    iomanip
    -0.32
    .),
    -0.32
     meda
    -0.31
     Itália
    -0.31
    Med
    -0.31
     cruising
    -0.30
     medically
    -0.29
    POSITIVE LOGITS
     Specifies
    0.61
    ientôt
    0.61
     Removes
    0.60
     Reply
    0.59
     Arkivert
    0.57
     Deletes
    0.57
     Deleted
    0.56
    <bos>
    0.56
     Monfieur
    0.56
     Loops
    0.55
    Activations Density 29.870%

    No Known Activations