© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15309
    Prev
    Next
    INDEX
    Explanations

    text containing hedging language and tentative statements like 'may', 'could', 'would', 'can', 'it is thought', and trial.

    oai_token-act-pair · gemini-2.0-flash

    Negation words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ConstraintMaker
    -1.05
     betweenstory
    -0.98
    RectangleBorder
    -0.96
    providedIn
    -0.88
    findpost
    -0.88
     صوتيه
    -0.84
    InSection
    -0.82
    AddTagHelper
    -0.82
     تانيه
    -0.81
    AxisAlignment
    -0.80
    POSITIVE LOGITS
     did
    0.81
     cannot
    0.79
     does
    0.78
     Cannot
    0.67
    cannot
    0.63
    Cannot
    0.59
     do
    0.53
    did
    0.52
    does
    0.50
    <strong>
    0.48
    Activations Density 5.331%

    No Known Activations