© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4917
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives related to past experience and agreement/acceptance

    oai_token-act-pair · gemini-2.0-flash

    past-participle verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     betweenstory
    -0.73
    +:+
    -0.67
    tvguidetime
    -0.67
    Personendaten
    -0.66
     sarebbero
    -0.66
     nationaux
    -0.63
     seraient
    -0.63
     mères
    -0.62
     Partagez
    -0.62
     rayures
    -0.61
    POSITIVE LOGITS
    bootstrapcdn
    0.62
    <bos>
    0.47
     });
    0.47
    ̎
    0.45
    ?».
    0.44
     nought
    0.44
    ggior
    0.44
    ReferenceEquals
    0.43
    Newswire
    0.43
    </caption>
    0.42
    Activations Density 0.383%

    No Known Activations