© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10846
    Prev
    Next
    INDEX
    Explanations

    the substring "ip raz" in words, perhaps as part of medical or scientific terms

    oai_token-act-pair · gemini-2.0-flash

    "ip"-containing words

    np_max-act · gemini-2.0-flash

    ip

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    패
    -0.55
    memberof
    -0.54
    pace
    -0.54
     Lyndon
    -0.52
     neutral
    -0.51
     Fol
    -0.51
    েই
    -0.50
     handker
    -0.50
    setTransform
    -0.50
    PART
    -0.50
    POSITIVE LOGITS
    Portale
    0.82
    pis
    0.79
    itudinal
    0.72
    piar
    0.70
     <<<<<<<<<<<<<<
    0.69
    piram
    0.66
    pi
    0.66
     Pira
    0.65
     Pi
    0.64
    PIS
    0.64
    Activations Density 0.279%

    No Known Activations