© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80529
    Prev
    Next
    INDEX
    Explanations

    published in

    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_31_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
     Holman
    0.38
     말
    0.38
    స్తుంది
    0.38
     Speaking
    0.37
    뒷
    0.36
     Nummer
    0.36
    آخر
    0.36
     nossas
    0.36
     outward
    0.35
    続け
    0.35
    POSITIVE LOGITS
     kayna
    0.45
    穵
    0.39
     vasena
    0.38
    Claude
    0.37
    街道
    0.37
     केमिक
    0.36
     nain
    0.36
    дца
    0.35
     iha
    0.35
     nervously
    0.35
    Activations Density 0.000%

    No Known Activations