© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141637
    Prev
    Next
    INDEX
    Explanations

    explico

    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_12_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
    𝚢
    0.60
    বের
    0.59
    喜剧
    0.59
    것
    0.59
    ופ
    0.58
     Anosov
    0.58
    亣
    0.58
     चैप्टर्स
    0.56
    敉
    0.56
    ocurrencies
    0.55
    POSITIVE LOGITS
     trabajar
    0.57
     concluir
    0.57
    Working
    0.56
     working
    0.53
     time
    0.53
    Workspace
    0.53
     can
    0.52
     Working
    0.52
    zić
    0.52
    Prote
    0.51
    Activations Density 0.001%

    No Known Activations