© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8238
    Prev
    Next
    INDEX
    Explanations

    phrases utilizing prepositions to indicate location or direction.

    oai_token-act-pair · gemini-2.0-flash

    Code and article snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Métro
    -0.47
     Palacio
    -0.45
     ſte
    -0.44
     ſtre
    -0.44
     juſt
    -0.44
    Metro
    -0.43
    خصة
    -0.42
     encantó
    -0.42
     Trojan
    -0.42
    zten
    -0.42
    POSITIVE LOGITS
    AndroidJUnit
    0.69
    MigrationBuilder
    0.68
     autorytatywna
    0.66
    tagHelperRunner
    0.66
     utafitiHapana
    0.65
    odiment
    0.65
    AndEndTag
    0.64
    scalatest
    0.64
     parts
    0.63
    Vidite
    0.63
    Activations Density 0.563%

    No Known Activations