© 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. 13697
    Prev
    Next
    INDEX
    Explanations

    metaphors and idioms related to vision and comprehension

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "picture"

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

    picture

    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
    Попис
    -0.59
    yntaxException
    -0.56
    </thead>
    -0.53
    cible
    -0.52
    fhir
    -0.51
    ItemBackground
    -0.50
    ftagPool
    -0.50
     DELLE
    -0.50
    鰭
    -0.49
    хьтан
    -0.49
    POSITIVE LOGITS
     picture
    2.86
    picture
    2.45
     Picture
    2.34
    Picture
    2.23
     PICTURE
    2.14
     pictures
    1.99
    PICTURE
    1.76
     pic
    1.75
    pictures
    1.64
     Pictures
    1.58
    Activations Density 1.745%

    No Known Activations