© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11537
    Prev
    Next
    INDEX
    Explanations

    words connecting one action to a desired outcome

    oai_token-act-pair · gemini-2.0-flash

    Technical instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     itſelf
    -1.18
     poffible
    -1.05
     iſt
    -1.02
     ſche
    -1.02
     myſelf
    -1.02
     auffi
    -1.00
     ſeveral
    -0.99
     Monfieur
    -0.99
     Efq
    -0.99
     Jefus
    -0.97
    POSITIVE LOGITS
     "
    0.67
    :
    0.67
     “
    0.61
     '
    0.57
     consider
    0.55
     include
    0.55
     insert
    0.55
     ‘
    0.53
     purchase
    0.53
     import
    0.52
    Activations Density 6.001%

    No Known Activations