© 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. 3026
    Prev
    Next
    INDEX
    Explanations

    the syllable "ma"

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'ma'

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

    ma

    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
    intervento
    -0.57
     fotografico
    -0.49
     بلکه
    -0.48
     marquées
    -0.48
     setempat
    -0.46
     metálica
    -0.46
     ferdig
    -0.45
     spéciale
    -0.45
     Cæsar
    -0.44
    ENSES
    -0.44
    POSITIVE LOGITS
    ReusableCell
    0.79
    uxxxx
    0.77
    IsMutable
    0.70
    AndEndTag
    0.69
     חיצוניים
    0.68
     فريبيس
    0.67
     MainAxisSize
    0.66
     transfieras
    0.63
     AssemblyCulture
    0.59
    RenderAtEndOf
    0.58
    Activations Density 0.375%

    No Known Activations