© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12141
    Prev
    Next
    INDEX
    Explanations

    phrases about location, particularly about whether you are in some location

    oai_token-act-pair · gemini-2.0-flash

    location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    [--
    -0.54
    EDEFAULT
    -0.50
    ubility
    -0.46
    logeny
    -0.46
    icha
    -0.44
    pausal
    -0.44
     depend
    -0.43
    — 
    -0.42
    ilen
    -0.41
    cian
    -0.41
    POSITIVE LOGITS
     utafitiHapana
    0.84
    ($__
    0.72
     snippetHide
    0.68
    DockStyle
    0.67
    Datuak
    0.65
     autorytatywna
    0.63
    LookAnd
    0.61
    WithIOException
    0.61
    UnsafeEnabled
    0.58
     surla
    0.58
    Activations Density 0.735%

    No Known Activations