© 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. 13714
    Prev
    Next
    INDEX
    Explanations

    question and answer pairs or code blocks that are asking for or giving advice.

    oai_token-act-pair · gemini-2.0-flash

    Question words

    np_max-act-logits · gemini-2.0-flash

    interrogative words

    np_token-act-pair-logits · gpt-4o-mini
    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
    ERI
    -0.46
    ots
    -0.44
    ott
    -0.43
     circle
    -0.42
    ale
    -0.42
    וז
    -0.41
     pel
    -0.41
     forces
    -0.41
     door
    -0.41
     dou
    -0.40
    POSITIVE LOGITS
    Is
    1.30
     Is
    1.30
    Are
    1.21
     Are
    1.18
    Does
    1.15
     Does
    1.09
     האם
    1.03
     apakah
    0.98
     Shall
    0.98
    آیا
    0.95
    Activations Density 5.792%

    No Known Activations