© 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. 14745
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns expressing an opinion or thought

    oai_token-act-pair · gemini-2.0-flash

    pronouns and common conjunctions

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

    Expressing thoughts/opinions

    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
     الحره
    -0.93
    ValueStyle
    -0.86
     виправивши
    -0.83
    Diweddarwch
    -0.80
     pleaſure
    -0.79
    存于互联网档案馆
    -0.79
     дописавши
    -0.79
    WithIOException
    -0.78
     صوتيه
    -0.75
     Efq
    -0.73
    POSITIVE LOGITS
     think
    0.51
     really
    0.46
     at
    0.45
    und
    0.42
    Kru
    0.40
     first
    0.40
    simpleType
    0.40
     Krieges
    0.40
     r
    0.38
     gia
    0.38
    Activations Density 1.678%

    No Known Activations