© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14605
    Prev
    Next
    INDEX
    Explanations

    personal experiences, opinions and reflections, often indicated by personal pronouns and related verbs

    oai_token-act-pair · gemini-2.0-flash

    past tense activities

    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
    principalTable
    -0.68
    InjectAttribute
    -0.66
     nakalista
    -0.63
     said
    -0.62
    XmlAccessType
    -0.61
    findpost
    -0.61
     accused
    -0.59
     announced
    -0.59
     meinte
    -0.58
     revealed
    -0.57
    POSITIVE LOGITS
     exercised
    0.65
     fished
    0.63
     practiced
    0.63
     practised
    0.62
     wielded
    0.60
     played
    0.60
     utilized
    0.60
     serviced
    0.60
     enforced
    0.58
     Played
    0.58
    Activations Density 6.281%

    No Known Activations