© 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. 137545
    Prev
    Next
    INDEX
    Explanations

    malicious malware malnutrition

    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
    hygine
    0.52
    sai
    0.52
    oxins
    0.51
    v
    0.51
    s
    0.50
     Bact
    0.48
    fusion
    0.47
    ק
    0.47
     Approx
    0.46
    います
    0.46
    POSITIVE LOGITS
     исти
    0.50
     et
    0.49
     العد
    0.48
     выбора
    0.47
     '}
    0.47
     })),
    0.47
     للم
    0.47
    },
    0.47
     spouses
    0.47
     للس
    0.47
    Activations Density 0.001%

    No Known Activations