© 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. 11301
    Prev
    Next
    INDEX
    Explanations

    text that's similar to an instruction manual

    oai_token-act-pair · gemini-2.0-flash

    Instructions

    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
     متعلقه
    -0.60
     Roskov
    -0.56
     Allí
    -0.54
     typelib
    -0.53
     singularity
    -0.50
    ContentAsync
    -0.50
     Flü
    -0.48
    vacy
    -0.48
    誰も
    -0.47
    jalá
    -0.47
    POSITIVE LOGITS
    Einzelnachweise
    0.64
    mson
    0.55
    msgSender
    0.54
    randomUUID
    0.53
    principalColumn
    0.53
    anstalt
    0.52
    yons
    0.52
    তথ্যসূত্র
    0.51
    Izvori
    0.50
     piede
    0.49
    Activations Density 1.028%

    No Known Activations