© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86633
    Prev
    Next
    INDEX
    Explanations

    examine, look, check, peering

    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_23_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
     anu
    0.46
     pert
    0.43
     freezer
    0.41
     bianca
    0.41
     atas
    0.40
     Z
    0.40
     berhenti
    0.40
     pronta
    0.39
     फ्रिज
    0.38
    Pert
    0.38
    POSITIVE LOGITS
    howto
    0.47
    idname
    0.42
    缺
    0.40
    streetmap
    0.40
    proportion
    0.38
    vocabulary
    0.38
    otrop
    0.38
     proportion
    0.38
    merz
    0.38
    arus
    0.36
    Activations Density 0.004%

    No Known Activations