© 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. 11060
    Prev
    Next
    INDEX
    Explanations

    content in French

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act-logits · gemini-2.0-flash

    de

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     myſelf
    -1.17
    ſelf
    -1.14
     Efq
    -1.13
     faſt
    -1.13
     iſt
    -1.12
    ſelves
    -1.10
     Jefus
    -1.09
     itſelf
    -1.09
     photolibrary
    -1.08
     purpoſe
    -1.08
    POSITIVE LOGITS
     N
    0.51
     H
    0.48
     F
    0.48
     O
    0.44
     c
    0.43
     veik
    0.42
     Mar
    0.42
     Y
    0.42
     M
    0.41
     V
    0.40
    Activations Density 1.144%

    No Known Activations