© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3934
    Prev
    Next
    INDEX
    Explanations

    the word "promise"

    oai_token-act-pair · gemini-2.0-flash

    promise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -1.09
     an
    -0.88
     a
    -0.85
     his
    -0.82
     her
    -0.66
     both
    -0.65
     non
    -0.65
     con
    -0.65
     di
    -0.60
     un
    -0.59
    POSITIVE LOGITS
     Houſe
    1.33
     Monfieur
    1.26
     Reſ
    1.23
     Anſ
    1.21
     Diſ
    1.19
     Chriftian
    1.18
     Shakspeare
    1.17
     Efq
    1.13
     Perſ
    1.12
     Hift
    1.10
    Activations Density 1.705%

    No Known Activations