© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15000
    Prev
    Next
    INDEX
    Explanations

    mixed text and numbers, often related to code snippets or numeric data with surrounding text

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    httphttps
    -0.81
    EDEFAULT
    -0.69
    styleType
    -0.65
     SwitchCompat
    -0.65
     okuyayım
    -0.64
    MergeFrom
    -0.63
    eseorang
    -0.63
    RuleContext
    -0.63
     bezeichneter
    -0.60
    MemoryWarning
    -0.59
    POSITIVE LOGITS
     box
    0.47
    ersen
    0.47
     surla
    0.44
     mis
    0.43
     Ab
    0.43
     Box
    0.40
    ANEOUS
    0.39
     cyto
    0.39
    国の
    0.39
    farin
    0.38
    Activations Density 0.544%

    No Known Activations