© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13671
    Prev
    Next
    INDEX
    Explanations

    instances of people being unhappy or disagreeing with things

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AttributeSet
    -0.60
     चीज़ों
    -0.53
    LookAnd
    -0.53
    TagHelpers
    -0.52
     SafeMath
    -0.51
    SourceChecksum
    -0.50
     chi̍t
    -0.49
     strtotime
    -0.48
     noDo
    -0.48
    PhysRevD
    -0.48
    POSITIVE LOGITS
     off
    2.75
     Off
    2.44
    Off
    2.42
    off
    2.41
     OFF
    2.11
    OFF
    1.98
    offs
    1.63
     offs
    1.56
    オフ
    1.47
     オフ
    1.17
    Activations Density 4.216%

    No Known Activations