© 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. 199066
    Prev
    Next
    INDEX
    Explanations

    security protections exploit mitigations

    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
    lama
    0.59
    Manifest
    0.55
    Roma
    0.55
    Sud
    0.54
    Gul
    0.54
    Sunglasses
    0.53
    さ
    0.52
    선
    0.52
    María
    0.52
    Sono
    0.51
    POSITIVE LOGITS
     n
    0.54
     table
    0.49
     whispered
    0.48
     box
    0.46
     proximity
    0.46
     position
    0.46
     hints
    0.45
     neuro
    0.45
     baked
    0.45
     drawer
    0.45
    Activations Density 0.001%

    No Known Activations