© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10190
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to locations, especially businesses and corners.

    oai_token-act-pair · gemini-2.0-flash

    corner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     corner
    -1.59
    corner
    -1.35
     CORNER
    -1.30
     Corner
    -1.22
     corners
    -1.16
    io
    -1.15
    Corner
    -1.12
     Corners
    -0.96
    Corners
    -0.91
    corners
    -0.90
    POSITIVE LOGITS
    tagHelperRunner
    0.81
     ContentValues
    0.67
     surla
    0.65
     Audiodateien
    0.63
    tagHelper
    0.60
     edits
    0.59
     ſeveral
    0.57
    undred
    0.57
    ariConfig
    0.56
     caufe
    0.56
    Activations Density 9.970%

    No Known Activations