© 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. 10881
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, single-character tokens, and words related to Canada

    oai_token-act-pair · gemini-2.0-flash

    end of sentences

    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
     –
    -0.38
     -
    -0.30
     --
    -0.30
     ob
    -0.29
     Италијани
    -0.29
     ver
    -0.29
    .
    -0.29
     ta
    -0.28
    /*---
    -0.28
    StatusEnum
    -0.28
    POSITIVE LOGITS
     houſe
    0.94
     faſt
    0.89
     myſelf
    0.84
     Monfieur
    0.83
     ſtate
    0.82
     Efq
    0.82
     preſent
    0.82
     cauſe
    0.82
     uſe
    0.81
     pleaſure
    0.81
    Activations Density 5.969%

    No Known Activations