© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15036
    Prev
    Next
    INDEX
    Explanations

    phrases where something is not something else

    oai_token-act-pair · gemini-2.0-flash

    Negative sentiment, advice

    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
     >=",
    -0.59
    Lähteet
    -0.55
    $"
    -0.51
     թվական
    -0.47
    ]="
    -0.47
     发表于
    -0.47
    $'
    -0.46
    '][$
    -0.46
     combineReducers
    -0.46
    ]=$
    -0.45
    POSITIVE LOGITS
     pres
    0.57
    webgl
    0.57
     Pres
    0.56
    δά
    0.56
    chanical
    0.55
    LookAnd
    0.52
     ContentValues
    0.51
     Horv
    0.50
    RegressionTest
    0.50
     Alha
    0.49
    Activations Density 0.574%

    No Known Activations