© 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. 3130
    Prev
    Next
    INDEX
    Explanations

    first person pronouns in relation to action

    oai_token-act-pair · gemini-2.0-flash

    actions related to removal or replacement

    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
     appartient
    -0.54
    الدراسه
    -0.53
     unknownFields
    -0.49
     '\\;'
    -0.49
     avoient
    -0.47
     păr
    -0.47
     Mbappe
    -0.46
    liculas
    -0.46
     épaules
    -0.46
     mijne
    -0.46
    POSITIVE LOGITS
    rungsseite
    0.71
     Administrativna
    0.59
    +#+
    0.58
     remove
    0.58
     تضيفلها
    0.57
    ImageContext
    0.56
    verwijspagina
    0.56
     replaced
    0.54
     removed
    0.54
     chang
    0.54
    Activations Density 2.056%

    No Known Activations