© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139101
    Prev
    Next
    INDEX
    Explanations

    prompt message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rupt
    0.40
    బడి
    0.38
     시민
    0.37
    命
    0.36
     Pä
    0.36
     bacterium
    0.36
    cornell
    0.36
    夷
    0.36
    共和国
    0.35
     auxin
    0.35
    POSITIVE LOGITS
     message
    1.31
     messages
    1.30
     mensagem
    1.23
    メッセージ
    1.23
     mensaje
    1.17
     mesaj
    1.16
    message
    1.16
     Messages
    1.16
     mensajes
    1.14
     mensagens
    1.13
    Activations Density 0.007%

    No Known Activations