© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13433
    Prev
    Next
    INDEX
    Explanations

    references to parts of the head or expressions using "head"

    oai_token-act-pair · gemini-2.0-flash

    body parts

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

    thoughts and feelings

    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
     <=",
    -0.49
    ẵn
    -0.49
    nP
    -0.46
     незавершена
    -0.46
    สา
    -0.46
     CreateTagHelper
    -0.45
    men
    -0.43
    Décès
    -0.43
    évaluateur
    -0.42
    vertret
    -0.42
    POSITIVE LOGITS
     eyes
    1.35
     head
    1.34
     mind
    1.30
     mouth
    1.23
     ears
    1.23
     throat
    1.16
     lungs
    1.10
     feet
    1.05
    head
    1.03
     face
    1.02
    Activations Density 0.912%

    No Known Activations