© 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. 13415
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with the subject of a review or story.

    oai_token-act-pair · gemini-2.0-flash

    negative comments

    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
     ActivatedRoute
    -0.46
    Clik
    -0.46
     län
    -0.35
     urbaine
    -0.35
     rurale
    -0.35
    PageContext
    -0.35
     gemeenten
    -0.34
     Rakyat
    -0.33
    EndInit
    -0.33
    主任
    -0.33
    POSITIVE LOGITS
     myſelf
    0.86
     Monfieur
    0.85
    =$?
    0.85
     Majefty
    0.85
    ^(@)
    0.80
    ſelf
    0.78
    ंदीखरीदारी
    0.77
     pleaſure
    0.75
     Efq
    0.73
    BRUARY
    0.72
    Activations Density 4.821%

    No Known Activations