© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6999
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to authority, requests and permissions

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'leave' and related terms

    np_token-act-pair-logits · gpt-4o-mini

    Permission/leave

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     snippetHide
    -0.63
     récomp
    -0.54
     remporté
    -0.49
     juger
    -0.49
     Forderungen
    -0.48
     staden
    -0.47
     franceses
    -0.47
     fordert
    -0.47
     refroid
    -0.46
     témoin
    -0.45
    POSITIVE LOGITS
     leave
    1.67
    leave
    1.49
     Leave
    1.46
    Leave
    1.46
     LEAVE
    1.30
     permission
    1.28
    LEAVE
    1.14
    permission
    1.11
     Permission
    0.97
     permiso
    0.96
    Activations Density 2.733%

    No Known Activations