© 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
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12576
    Prev
    Next
    INDEX
    Explanations

    horizontal lines and/or end of sentences

    oai_token-act-pair · gemini-2.0-flash

    Section delimiters/cutoffs

    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
    parsedMessage
    -0.82
    AsUp
    -0.63
    __*/
    -0.61
    IVEREF
    -0.60
    Jeografia
    -0.58
    Portail
    -0.54
    burger
    -0.52
    WireFormat
    -0.52
    .")
    -0.52
    IsInitialized
    -0.51
    POSITIVE LOGITS
    imageshack
    0.56
     विश्वसनीयता
    0.55
    ⓧ
    0.40
    thorpe
    0.38
    ælp
    0.37
     HttpNotFound
    0.36
    cellence
    0.36
     finite
    0.36
     mouseClicked
    0.35
    amond
    0.34
    Activations Density 0.272%

    No Known Activations