© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7390
    Prev
    Next
    INDEX
    Explanations

    mentions of going from one place or location to another

    oai_token-act-pair · gemini-2.0-flash

    land and shore

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    chappement
    -0.52
    toMatchSnapshot
    -0.47
    rsiniz
    -0.47
     становника
    -0.46
    adaptiveStyles
    -0.46
    gameserver
    -0.42
    essoal
    -0.41
    TintMode
    -0.40
     sähkö
    -0.40
    entgen
    -0.40
    POSITIVE LOGITS
     land
    1.06
     shore
    1.03
    land
    0.92
     lands
    0.88
    LAND
    0.86
     ground
    0.86
     soil
    0.85
     dry
    0.84
     mainland
    0.84
     LAND
    0.83
    Activations Density 0.526%

    No Known Activations