© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 68096
    Prev
    Next
    INDEX
    Explanations

    injury/harm

    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_51_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
     kek
    0.45
    원
    0.43
     東京都
    0.42
    fence
    0.40
     Syr
    0.40
     Orig
    0.39
    cattle
    0.39
     Sul
    0.38
    iben
    0.38
    Benzyl
    0.38
    POSITIVE LOGITS
     inj
    0.51
     injuries
    0.44
     Inj
    0.43
    inj
    0.43
    垷
    0.42
     injure
    0.42
     Injuries
    0.40
    rej
    0.38
    Inj
    0.38
     Verlet
    0.38
    Activations Density 0.001%

    No Known Activations