© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5502
    Prev
    Next
    INDEX
    Explanations

    words relating to horizontal and vertical orientation and layout

    oai_token-act-pair · gemini-2.0-flash

    vertical or horizontal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     vertical
    -2.44
     Vertical
    -2.30
     horizontal
    -2.28
    vertical
    -2.25
     Horizontal
    -2.20
    Vertical
    -2.19
    horizontal
    -2.14
    Horizontal
    -2.08
     verticale
    -1.95
     VERTICAL
    -1.92
    POSITIVE LOGITS
    :^(
    0.60
    protoc
    0.58
     ce
    0.53
    ופת
    0.52
    bouncycastle
    0.51
     MediaPlayer
    0.50
     cit
    0.48
    GetMapping
    0.48
    DataOutputStream
    0.48
    通
    0.47
    Activations Density 4.457%

    No Known Activations