© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217165
    Prev
    Next
    INDEX
    Explanations

    Photographer, portraits, Leibovitz

    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
    armos
    0.35
    claimed
    0.35
    撤
    0.35
    罪
    0.35
    support
    0.34
    днев
    0.34
     nasa
    0.34
     اختی
    0.33
    mapped
    0.33
     ग्लू
    0.33
    POSITIVE LOGITS
     Hadrian
    0.40
    طر
    0.38
     Riccardo
    0.38
    嗟
    0.38
     pianta
    0.37
    Nicolas
    0.37
    ග
    0.37
     intimidating
    0.37
     extremo
    0.36
    corso
    0.36
    Activations Density 0.000%

    No Known Activations