© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11632
    Prev
    Next
    INDEX
    Explanations

    legal and medical terminology, including individuals involved and the concept of 'if'

    oai_token-act-pair · gemini-2.0-flash

    consider

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Second
    -0.69
    second
    -0.67
    Second
    -0.66
     second
    -0.62
     Rhe
    -0.55
    SECOND
    -0.54
     SECOND
    -0.54
     vote
    -0.54
    istible
    -0.54
    kompet
    -0.49
    POSITIVE LOGITS
     consider
    1.30
     considered
    1.23
    Consider
    1.19
     Considered
    1.18
     Consider
    1.16
     CONSIDER
    1.15
     considers
    1.15
    considered
    1.14
    consider
    1.11
     consid
    1.06
    Activations Density 4.239%

    No Known Activations