© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6608
    Prev
    Next
    INDEX
    Explanations

    the word "off"

    oai_token-act-pair · gemini-2.0-flash

    off

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     off
    -2.81
     Off
    -2.38
    Off
    -2.30
    off
    -2.11
     OFF
    -2.06
    OFF
    -1.87
     offs
    -1.61
    offs
    -1.51
    オフ
    -1.50
     オフ
    -1.23
    POSITIVE LOGITS
    EndInit
    0.72
    EndGlobalSection
    0.58
    enumi
    0.58
    lably
    0.56
     BoxFit
    0.55
    Життєпис
    0.54
     يتيمه
    0.54
     AssemblyTitle
    0.53
    BackStack
    0.53
    amenta
    0.53
    Activations Density 0.690%

    No Known Activations