© 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. 7995
    Prev
    Next
    INDEX
    Explanations

    a variety of common helping verbs

    oai_token-act-pair · gemini-2.0-flash

    quality descriptors related to acceptability

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

    State of being/description

    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
    ThemeOverlay
    -0.80
     Cæsar
    -0.67
     INTERESAR
    -0.64
    @[+][
    -0.63
     chi̍t
    -0.63
     Theſe
    -0.62
     Shakspeare
    -0.62
     صوتيه
    -0.61
     surla
    -0.60
    neſs
    -0.59
    POSITIVE LOGITS
    fjspx
    0.64
     fine
    0.50
     attes
    0.47
     acceptable
    0.46
    fine
    0.45
     ideales
    0.44
    record
    0.44
     상세
    0.44
     desirable
    0.43
    ollectionView
    0.43
    Activations Density 1.409%

    No Known Activations