© 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. 2869
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, especially "can", "have", "was", and their contractions.

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

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

    subjective statements

    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
     not
    -2.59
    not
    -2.02
    Not
    -1.73
     Not
    -1.73
    NOT
    -1.46
     NOT
    -1.38
     bukan
    -1.34
     nicht
    -1.32
     ikke
    -1.16
     نه
    -1.14
    POSITIVE LOGITS
     propOrder
    0.55
     EconPapers
    0.47
    AndEndTag
    0.47
    n
    0.46
     (_,
    0.44
    N
    0.43
    StylePriority
    0.41
    ModelForm
    0.39
    GEBURTSDATUM
    0.38
    (&:
    0.38
    Activations Density 1.337%

    No Known Activations