© 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. 9706
    Prev
    Next
    INDEX
    Explanations

    the string "tmp"

    oai_token-act-pair · gemini-2.0-flash

    tmp

    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
     revanche
    -0.53
     aren
    -0.49
    i
    -0.48
     onto
    -0.48
     levier
    -0.47
     themselves
    -0.46
    Disclosures
    -0.45
    .
    -0.45
     weren
    -0.45
     jednocześnie
    -0.44
    POSITIVE LOGITS
     متعلقه
    1.17
    SourceChecksum
    1.16
    DoubleQuotes
    0.96
    SequentialGroup
    0.96
     nahilalakip
    0.92
     ModelExpression
    0.91
    IsMutable
    0.91
    ]){
    0.89
    URLException
    0.89
    StoryboardSegue
    0.88
    Activations Density 0.263%

    No Known Activations