© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27809
    Prev
    Next
    INDEX
    Explanations

    Gemini Ultra

    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_40_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
    வீ
    0.44
     sort
    0.34
     &$
    0.34
    াম
    0.33
     ইন্ড
    0.33
    Ví
    0.33
    aber
    0.33
     Sort
    0.33
    庝
    0.32
    üü
    0.32
    POSITIVE LOGITS
     spirits
    0.40
     feeling
    0.39
    Pilot
    0.38
    朋
    0.38
     lustre
    0.38
    eteenth
    0.37
     transgression
    0.37
     pilot
    0.37
     séance
    0.37
     Pilot
    0.36
    Activations Density 0.008%

    No Known Activations