© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10932
    Prev
    Next
    INDEX
    Explanations

    tokens that might appear in a conversation ("me", "he", "te", "tu", "no")

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the pronoun 'me'

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

    me/te

    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
     '\\;'
    -1.03
    Personendaten
    -0.98
     typelib
    -0.84
     Efq
    -0.82
    OGND
    -0.80
     AssemblyCulture
    -0.80
     transfieras
    -0.80
     myſelf
    -0.80
    abetes
    -0.79
     fevere
    -0.79
    POSITIVE LOGITS
    iver
    0.47
    興
    0.46
     acuerdo
    0.44
    fflush
    0.42
     van
    0.41
     h
    0.41
     They
    0.41
    vin
    0.40
    IVER
    0.40
     inter
    0.40
    Activations Density 0.938%

    No Known Activations