© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3390
    Prev
    Next
    INDEX
    Explanations

    words related to computer file manipulation or specific HIV subtypes

    oai_token-act-pair · gemini-2.0-flash

    filelist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    evaluator
    -1.12
    shutil
    -1.06
     
    -1.05
    memcmp
    -1.00
    outdir
    -0.98
    operands
    -0.96
    decrypted
    -0.94
    usleep
    -0.93
    eventId
    -0.88
     I
    -0.88
    POSITIVE LOGITS
     MainAxisSize
    1.27
     lenker
    1.14
    windowFixed
    1.13
    ImageContext
    1.09
    parsedMessage
    1.08
     AssemblyCulture
    1.07
    protoimpl
    1.07
    ftagPool
    1.05
    nocache
    1.05
     linkovi
    1.05
    Activations Density 2.762%

    No Known Activations