© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11572
    Prev
    Next
    INDEX
    Explanations

    scientific prose expressing agreement between observations and theoretical models

    oai_token-act-pair · gemini-2.0-flash

    positive assessments or reviews

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

    good agreement

    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
     pyplot
    -0.50
    OLPH
    -0.49
    DidChange
    -0.47
    ########.
    -0.46
     printf
    -0.46
    printf
    -0.46
    RowIndex
    -0.46
    曖昧さ回避
    -0.46
    AZIONI
    -0.45
    reactstrap
    -0.44
    POSITIVE LOGITS
     good
    1.00
     agreement
    0.92
    Good
    0.89
    good
    0.88
     Good
    0.85
     excellent
    0.84
     GOOD
    0.82
    excellent
    0.81
     dobry
    0.80
    agreement
    0.75
    Activations Density 4.308%

    No Known Activations