© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11611
    Prev
    Next
    INDEX
    Explanations

    references to highways, interstates, and roads

    oai_token-act-pair · gemini-2.0-flash

    highways

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     صوتيه
    -0.57
     AspNetCore
    -0.53
    tableFuture
    -0.52
    astu
    -0.52
    pexpr
    -0.52
    transport
    -0.52
    ])))
    -0.51
    upat
    -0.50
    upun
    -0.50
     Lut
    -0.49
    POSITIVE LOGITS
    पया
    0.56
    ագրություններ
    0.55
    setVerticalGroup
    0.50
     Krim
    0.48
    قایناقلار
    0.48
     DBNull
    0.48
     Serp
    0.45
     Umständen
    0.45
     dévelo
    0.44
    exitRule
    0.44
    Activations Density 1.328%

    No Known Activations