© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31273
    Prev
    Next
    INDEX
    Explanations

    build bomb

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     mastermind
    0.44
     peer
    0.39
    KindOfClass
    0.37
     Peer
    0.37
    Peer
    0.37
     coerc
    0.36
     R
    0.36
     siding
    0.35
    בר
    0.35
     브
    0.35
    POSITIVE LOGITS
    avali
    0.39
    LETE
    0.38
     quede
    0.37
    шок
    0.36
     Liet
    0.36
     puer
    0.35
     ڈ
    0.34
     Packed
    0.34
     quedar
    0.34
     trex
    0.33
    Activations Density 0.009%

    No Known Activations