© 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. 7798
    Prev
    Next
    INDEX
    Explanations

    code or configuration file syntax

    oai_token-act-pair · 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
     rhythm
    -0.68
     speed
    -0.64
     momentum
    -0.62
    speed
    -0.57
     ritmo
    -0.57
     pace
    -0.55
    rhythm
    -0.54
     aceler
    -0.54
     speeds
    -0.53
    momentum
    -0.53
    POSITIVE LOGITS
    enumi
    0.58
    βε
    0.56
    enumii
    0.54
     mesas
    0.51
     SqlCommand
    0.50
     يتيمه
    0.49
    laug
    0.48
    Schriften
    0.48
    ApiModelProperty
    0.48
    StructField
    0.48
    Activations Density 1.729%

    No Known Activations