© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4433
    Prev
    Next
    INDEX
    Explanations

    numbers larger than 1, especially those that involve the word "over"

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     kasarigan
    -1.38
    ]")]
    -1.31
    LookAnd
    -1.28
     nakalista
    -1.27
    ValueStyle
    -1.26
    AndEndTag
    -1.20
     Efq
    -1.13
    StoryboardSegue
    -1.12
     дописавши
    -1.11
     NSCoder
    -1.11
    POSITIVE LOGITS
    <bos>
    0.49
    j
    0.48
    o
    0.45
    ,
    0.43
     o
    0.42
    <eos>
    0.42
     dis
    0.42
    ng
    0.41
    <
    0.40
     (
    0.39
    Activations Density 2.438%

    No Known Activations