© 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. 7352
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs that indicate a state of being (is, was, are, been)

    oai_token-act-pair · gemini-2.0-flash

    programming language keywords

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

    was

    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
     hâte
    -0.59
    seamnă
    -0.47
    epy
    -0.46
    ască
    -0.46
     augmenté
    -0.45
     móveis
    -0.45
     masculina
    -0.45
    pearance
    -0.45
    yaitu
    -0.44
    owiak
    -0.44
    POSITIVE LOGITS
    ValueStyle
    0.76
    enterOuterAlt
    0.66
    delwed
    0.65
     שוליים
    0.65
    SOUNDBITE
    0.61
     gainera
    0.57
     صوتيه
    0.57
    ArgsConstructor
    0.57
    __((
    0.57
     severally
    0.55
    Activations Density 1.498%

    No Known Activations