© 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. 14902
    Prev
    Next
    INDEX
    Explanations

    words and phrases about traveling and returning home

    oai_token-act-pair · gemini-2.0-flash

    travel

    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
     BoxDecoration
    -0.68
    AutoScaleMode
    -0.59
    +#+#
    -0.59
    IsMutable
    -0.53
    ULAS
    -0.52
    ⓧ
    -0.51
    databind
    -0.51
    WebElementEntity
    -0.51
    ArrayAdapter
    -0.49
    ագրություններ
    -0.49
    POSITIVE LOGITS
     AttributeSet
    0.50
     right
    0.47
    ilateral
    0.47
     speaking
    0.46
    ämme
    0.46
    lami
    0.46
    fromnode
    0.45
    zungs
    0.44
    
    0.43
     here
    0.43
    Activations Density 1.750%

    No Known Activations