© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11592
    Prev
    Next
    INDEX
    Explanations

    ambiguous, seems to be looking for filenames and/or photo metadata and/or Latin names with associated dashes and possibly acronyms

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical data

    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
    гене
    -0.44
    DIPSETTING
    -0.43
    Obrázky
    -0.42
    fromCharCode
    -0.42
     u
    -0.42
     mig
    -0.41
     '
    -0.41
    .
    -0.39
    FunctionFlags
    -0.39
     >
    -0.39
    POSITIVE LOGITS
     purpoſe
    0.86
     reaſon
    0.82
     pleaſure
    0.81
     Reſ
    0.74
    GraphicsUnit
    0.73
     myſelf
    0.71
    neſs
    0.70
     ſtate
    0.69
     neceſſ
    0.68
     againſt
    0.68
    Activations Density 0.913%

    No Known Activations