© 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. 14465
    Prev
    Next
    INDEX
    Explanations

    the words "if", "is", "we", "they", "that, and "completely"

    oai_token-act-pair · gemini-2.0-flash

    programming syntax or keywords

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

    if

    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
     cannot
    -1.70
    cannot
    -1.58
     neither
    -1.52
     Cannot
    -1.46
     couldn
    -1.45
     unable
    -1.45
     couldnt
    -1.37
    neither
    -1.36
     CANNOT
    -1.34
    Cannot
    -1.32
    POSITIVE LOGITS
    +:+
    0.56
    enumi
    0.52
    ThemeOverlay
    0.48
    ynchronously
    0.48
     Infórmanos
    0.44
    ftagPool
    0.43
    sweetalert
    0.42
    Arbit
    0.41
    Ṭ
    0.40
    اذ
    0.40
    Activations Density 1.503%

    No Known Activations