© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11509
    Prev
    Next
    INDEX
    Explanations

    speech attribution

    oai_token-act-pair · gemini-2.0-flash

    “,”

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Efq
    -1.23
     Theſe
    -1.14
     myſelf
    -1.11
     Monfieur
    -1.08
     Reſ
    -1.07
     pleaſure
    -1.05
     itſelf
    -1.05
     ſche
    -1.02
     Shakspeare
    -1.02
     Houſe
    -1.00
    POSITIVE LOGITS
     he
    0.79
     a
    0.68
     the
    0.66
     say
    0.63
     "
    0.60
     an
    0.60
     co
    0.60
     noted
    0.60
     said
    0.59
     qui
    0.59
    Activations Density 4.515%

    No Known Activations